How to plot a nonlinear function in Support Vector Regression?

I want to plot the solved function of the SVM Regression method. The following code works fine with a linear Kernel, but not with nonlinear Kernels like "gauss" or "polynomial":

SVMR = fitrsvm(X,y,'KernelFunction','polynomial');
Y_response =(1/(SVMR.KernelParameters.Scale))*X*SVMR.Beta+SVMR.Bias;
plot(X,Y_response,'b');

i am getting the following error: "Error using * Inner matrix dimensions must agree."

Can somebody maybe help me with this? Would be so kind.

And is the loss function the only way to get a value of the goodness of the fit in SVM regression?

Kind regards, Sebastian Kaufmann