© 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. 6-RES-JB
    11. 3404
    Prev
    Next
    INDEX
    Explanations

    mentions of offensive positions in football

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.16
    0.9%
    1763
    +0.12
    0.6%
    1937
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1763
    +0.16
    0.03
    1008
    +0.12
    0.03
    1601
    +0.11
    0.03
    Negative Logits
    <bos>
    -3.30
    /**
    -1.22
    
    -1.15
    ⓧ
    -1.12
    <?
    -1.04
    /***
    -0.93
    /*
    -0.90
    <?
    -0.86
    /*++
    -0.72
    ///**
    -0.71
    POSITIVE LOGITS
     jaya
    1.24
     Minang
    1.20
     saar
    1.18
     maroc
    1.17
     panik
    1.16
     jawa
    1.16
     pank
    1.15
     seksi
    1.11
     bandung
    1.11
     Offensive
    1.09
    Activations Density 0.093%

    No Known Activations