It's a fairly straightforward shot that illustrates the concept or "cel levels" pretty well.
We've got four levels of animation plus the background. Each level is a cohesive series of drawings which run in sequence to make the illusion of movement. The background is stationary for the length of the shot.
This a stationary piece of art.
"TB" for thought balloon. This is a sequence of 14 drawings that animate up then cycle as a hold.
G for god. After the balloon animates up, this figure morphs on. This level has 16 drawings.
WL? wavy lines! This is a sequence of 11 cycling drawings that make a glowing halo around the figure.
D for dancer. This is a 10 drawing cycle. Unlike the others, it's not in registration -you can't just layer over and VOILA! perfect scene.
The dancers are mention to be duplicated and repositioned so we have several surrounding the god.
In the olden days this would be done in inking and with the photocopier. Today, it's a piece of cake in the animation composite in After Effects.
The composition looks like this:
You can see how the layering mimics an animation stand.
If you want your animation to resemble the movements of traditional cartoon animation, it's best to mimic the process as much as possible.
Again, this is a very simple scene with mostly effects animation and some generic dancing but the procedure is well illustrated.