© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2931
    Prev
    Next
    INDEX
    Explanations

    RSS feed subscription information

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    204
    +0.08
    0.3%
    871
    +0.08
    0.2%
    783
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.08
    0.02
    1456
    +0.08
    0.02
    1304
    +0.07
    0.02
    Negative Logits
    <bos>
    -1.22
     put
    -0.65
    ,
    -0.65
    HasAnnotation
    -0.64
    char
    -0.64
    改
    -0.64
     المدن
    -0.63
     in
    -0.63
    ́
    -0.63
    EndInit
    -0.63
    POSITIVE LOGITS
     RSS
    2.56
    RSS
    2.23
     stockholm
    2.06
     milano
    2.02
     eiffel
    1.95
     affor
    1.92
     milf
    1.90
     increa
    1.90
     lidl
    1.89
     panama
    1.88
    Activations Density 0.168%

    No Known Activations