Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Google DeepMind · Exploring Gemma 2 with Gemma Scope
Gemma-2-2B
MLP Out - 16k
22-GEMMASCOPE-MLP-16K
15849
Prev
Next
MODEL
22-gemmascope-mlp-16k
Source/SAE
INDEX
Go
Explanations
programming or technical code snippets with numbers, symbols, and computational language.
oai_token-act-pair · claude-3-5-haiku-20241022
Triggered by @jnainani
Avg Score: 44
specific dates and names related to events
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
Avg Score: 56
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-2B @ 22-gemmascope-mlp-16k
Configuration
google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
16,384
Data Type
float32
Hook Name
blocks.22.hook_mlp_out
Hook Layer
22
Architecture
jumprelu
Context Size
1,024
Dataset
monology/pile-uncopyrighted
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2-2b/22-gemmascope-mlp-16k/15849?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/22-gemmascope-mlp-16k/15849?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
5
-1.21
five
-1.13
Fifth
-1.13
fifth
-1.12
Five
-1.09
五
-1.03
５
-1.02
FIVE
-1.01
five
-1.00
Five
-0.96
POSITIVE LOGITS
8
0.56
八
0.53
oito
0.49
eight
0.48
eigh
0.48
2
0.48
eighth
0.48
1
0.47
nine
0.47
Eighteen
0.47
Act
ivations
Density 12.019%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
