diff --git a/FE b/FE
new file mode 100644
index 00000000000..e69de29bb2d
diff --git a/keras/src/layers/normalization/batch_normalization.py b/keras/src/layers/normalization/batch_normalization.py
index 8b0160344ee..67f12cab956 100644
--- a/keras/src/layers/normalization/batch_normalization.py
+++ b/keras/src/layers/normalization/batch_normalization.py
@@ -219,6 +219,18 @@ def build(self, input_shape):
         self.built = True
 
     def compute_output_shape(self, input_shape):
+        if isinstance(self.axis, int):
+            axes = [self.axis]
+        else:
+            axes = self.axis
+
+        for axis in axes:
+            if axis >= len(input_shape) or axis < -len(input_shape):
+                raise ValueError(
+                    f"Axis {axis} is out of bounds for "
+                    f"input shape {input_shape}. "
+                    f"Received: axis={self.axis}"
+                )
         return input_shape
 
     def call(self, inputs, training=None, mask=None):
diff --git a/keras/src/layers/normalization/group_normalization.py b/keras/src/layers/normalization/group_normalization.py
index f70fb69f3ed..c547c99a6b9 100644
--- a/keras/src/layers/normalization/group_normalization.py
+++ b/keras/src/layers/normalization/group_normalization.py
@@ -199,6 +199,18 @@ def _create_broadcast_shape(self, input_shape):
         return broadcast_shape
 
     def compute_output_shape(self, input_shape):
+        if isinstance(self.axis, int):
+            axes = [self.axis]
+        else:
+            axes = self.axis
+
+        for axis in axes:
+            if axis >= len(input_shape) or axis < -len(input_shape):
+                raise ValueError(
+                    f"Axis {axis} is out of bounds for "
+                    f"input shape {input_shape}. "
+                    f"Received: axis={self.axis}"
+                )
         return input_shape
 
     def get_config(self):
diff --git a/keras/src/layers/normalization/layer_normalization.py b/keras/src/layers/normalization/layer_normalization.py
index 73a8956fd8f..6df9fd1df89 100644
--- a/keras/src/layers/normalization/layer_normalization.py
+++ b/keras/src/layers/normalization/layer_normalization.py
@@ -117,7 +117,7 @@ def __init__(
         gamma_regularizer=None,
         beta_constraint=None,
         gamma_constraint=None,
-        **kwargs
+        **kwargs,
     ):
         super().__init__(**kwargs)
         if isinstance(axis, (list, tuple)):
@@ -235,6 +235,18 @@ def _broadcast(v):
         return ops.cast(outputs, input_dtype)
 
     def compute_output_shape(self, input_shape):
+        if isinstance(self.axis, int):
+            axes = [self.axis]
+        else:
+            axes = self.axis
+
+        for axis in axes:
+            if axis >= len(input_shape) or axis < -len(input_shape):
+                raise ValueError(
+                    f"Axis {axis} is out of bounds for "
+                    f"input shape {input_shape}. "
+                    f"Received: axis={self.axis}"
+                )
         return input_shape
 
     def get_config(self):
diff --git a/keras/src/testing/test_case.py b/keras/src/testing/test_case.py
index d5a8f7d779f..0d930f46dc4 100644
--- a/keras/src/testing/test_case.py
+++ b/keras/src/testing/test_case.py
@@ -43,7 +43,7 @@ def assertAllClose(self, x1, x2, atol=1e-6, rtol=1e-6, msg=None):
             x1 = backend.convert_to_numpy(x1)
         if not isinstance(x2, np.ndarray):
             x2 = backend.convert_to_numpy(x2)
-        np.testing.assert_allclose(x1, x2, atol=atol, rtol=rtol)
+        np.testing.assert_allclose(x1, x2, atol=atol, rtol=rtol, err_msg=msg)
 
     def assertNotAllClose(self, x1, x2, atol=1e-6, rtol=1e-6, msg=None):
         try:
@@ -62,7 +62,7 @@ def assertAlmostEqual(self, x1, x2, decimal=3, msg=None):
             x1 = backend.convert_to_numpy(x1)
         if not isinstance(x2, np.ndarray):
             x2 = backend.convert_to_numpy(x2)
-        np.testing.assert_almost_equal(x1, x2, decimal=decimal)
+        np.testing.assert_almost_equal(x1, x2, decimal=decimal, err_msg=msg)
 
     def assertAllEqual(self, x1, x2, msg=None):
         self.assertEqual(len(x1), len(x2), msg=msg)