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
Attention Out - 16k
0-GEMMASCOPE-ATT-16K
5
Prev
Next
MODEL
0-gemmascope-att-16k
Source/SAE
INDEX
Go
Explanations
attends to the same closing curly brace characters from various points based on the opening braces preceding them
oai_attention-head · gpt-4o-mini
Triggered by @bot
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-2B @ 0-gemmascope-att-16k
Configuration
google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
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.0.attn.hook_z
Hook Layer
0
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/0-gemmascope-att-16k/5?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/0-gemmascope-att-16k/5?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Head Attr Weights
0:
0.01
1:
0.05
2:
0.05
3:
0.04
4:
0.02
5:
0.72
6:
0.04
7:
0.04
Negative Logits
-0.71
-0.70
-0.68
myſelf
-0.62
-0.59
itſelf
-0.57
-0.56
-0.56
-0.54
-0.53
POSITIVE LOGITS
of
0.31
and
0.31
-
0.31
for
0.30
/
0.30
for
0.29
until
0.29
if
0.29
to
0.28
–
0.28
Act
ivations
Density 0.508%
Test
Steer
Stacked
Snippet
Full
Split DFA
Combine DFA
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations