x = tf.ones((2, 2))

with tf.GradientTape() as t:
  t.watch(x)
  y = tf.reduce_sum(x)
  z = tf.multiply(y, y)

# Derivative of z with respect to the original input tensor x
dz_dx = t.gradient(z, x)
for i in [0, 1]:
  for j in [0, 1]:
    assert dz_dx[i][j].numpy() == 8.0