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
Residual Stream - 16k
15-GEMMASCOPE-RES-16K
2459
Prev
Next
MODEL
15-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
terms related to safety and risk factors
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 @ 15-gemmascope-res-16k
Configuration
google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
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.15.hook_resid_post
Hook Layer
15
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/15-gemmascope-res-16k/2459?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/15-gemmascope-res-16k/2459?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
expandindo
-0.95
。】
-0.79
.)}
-0.78
'}>
-0.75
'))
-0.74
']))
-0.73
"])
-0.72
"]);
-0.72
Diwedd
-0.71
'])
-0.70
POSITIVE LOGITS
"
1.08
”
1.01
''
0.96
」
0.91
’’
0.91
""
0.89
"'
0.88
",
0.85
"!
0.80
\"
0.76
Act
ivations
Density 0.280%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
