Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Blog
Slack
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
Residual Stream - 16k
20-GEMMASCOPE-RES-16K
5061
Prev
Next
MODEL
20-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
indicators of breaks or inclusions in structured formats, such as programming or technical documentation
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-2B @ 20-gemmascope-res-16k
Configuration
google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
How To Load
Prompts (Dashboard)
36,864 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
16,384
Data Type
float32
Hook Name
blocks.20.hook_resid_post
Hook Layer
20
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/20-gemmascope-res-16k/5061?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/20-gemmascope-res-16k/5061?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
…
-0.93
…)
-0.87
՚
-0.82
….
-0.81
…~
-0.79
…”
-0.78
ſelves
-0.77
[…]
-0.76
…………
-0.76
(…)
-0.76
POSITIVE LOGITS
--
0.74
--
0.69
</h6>
0.67
...
0.63
0.60
</i>
0.58
&#
0.58
postIndex
0.58
'--
0.57
---
0.56
Act
ivations
Density 0.138%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
