© 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. 5138
    Prev
    Next
    INDEX
    Explanations

    representations and depictions in media, particularly focusing on portrayals of characters and social issues

    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
    +0.22
    1.2%
    1101
    +0.12
    0.7%
    1141
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1101
    +0.22
    0.02
    1141
    +0.12
    0.02
    61
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.85
    /***
    -0.83
    <?
    -0.70
    /*!
    -0.67
    
    -0.65
    //{
    -0.63
    <?
    -0.60
    ///**
    -0.59
    ⓧ
    -0.58
    glBind
    -0.56
    POSITIVE LOGITS
     thut
    1.09
     aen
    1.03
     kyo
    1.01
     haup
    1.01
     pollut
    1.00
     lill
    0.99
     daz
    0.98
     tramont
    0.98
     dises
    0.98
     thous
    0.97
    Activations Density 0.044%

    No Known Activations