© 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. 10-RES-JB
    11. 4883
    Prev
    Next
    INDEX
    Explanations

    references to men and gender comparisons

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.25
    0.9%
    2034
    +0.10
    0.4%
    1253
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    832
    +0.25
    0.06
    1438
    +0.10
    0.06
    1235
    +0.07
    0.05
    Negative Logits
    <bos>
    -2.81
     intersper
    -1.02
    ⓧ
    -0.97
    <?
    -0.96
    /***
    -0.88
    
    -0.81
     defray
    -0.81
    💼
    -0.79
    /**
    -0.78
     disbur
    -0.76
    POSITIVE LOGITS
     bandung
    0.71
     jawa
    0.70
    üyü
    0.69
     kaos
    0.69
     babi
    0.67
     kesi
    0.66
    masin
    0.65
     seksi
    0.64
     maske
    0.64
    başı
    0.64
    Activations Density 0.594%

    No Known Activations