Ah, I think I see what you're saying.

If you just want to remove the final layers and replace them with your own, you can do something like this:

NetChain[{
    (*the parts of the net you want to keep*)
    Take[net, 7], 
    (*the following are the replacement layers*)
    500, 
    Ramp,
    10,
    SoftmaxLayer[]
}]

Is that what you mean?

David P. -- I'm running on Windows 10. I did a NetTrain with TargetDevice -> GPU and it ran just fine on my EVGA 1080. Just to double check after seeing your post, I ran the code again, and indeed the GPU lights up with activity, so it is really in use.

Christopher -- Yes, changing the LearningRateMultiplier for the layers I want fixed is perfect. That combined with Sebastian's reminder about Drop will do what I want. And Matteo's alternate suggestion of saving out the Features is an interesting one, as I think it also does what I'd like, but in a different way. Thanks all. -- David