© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 616
    Prev
    Next
    INDEX
    Explanations

    words related to the act of approaching or making contact with something or someone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.19
    0.8%
    1407
    +0.15
    0.7%
    2004
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1407
    +0.19
    0.02
    2004
    +0.15
    0.02
    1325
    +0.14
    0.02
    Negative Logits
    <bos>
    -2.23
    bot
    -0.72
    def
    -0.70
    byte
    -0.70
     keep
    -0.69
    cout
    -0.69
    培
    -0.67
    lib
    -0.67
    public
    -0.67
    export
    -0.67
    POSITIVE LOGITS
     hentai
    1.75
     Minang
    1.72
     outlander
    1.70
     hairc
    1.70
     maneu
    1.70
     madonna
    1.67
     milf
    1.66
     casio
    1.65
     jurassic
    1.64
     stockholm
    1.63
    Activations Density 0.067%

    No Known Activations