The final loss gradient is 1D but network output is (1,2). How is the gradient propagated ?

I was wondering if the `tf.reduce_sum` and `y` are 1d and the mse cost term is 1d, however the gradient to be propagated needs to same dimension as network output i.e (1,ACTIONS) = (1,2). Is the final loss grad just replicated in both dimension ? i.e (1,1) -> (1,2) ?