© 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. 5111
    Prev
    Next
    INDEX
    Explanations

    terms related to critical societal and environmental 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
    +0.25
    1.1%
    1741
    +0.14
    0.6%
    1871
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.25
    0.06
    802
    +0.14
    0.07
    416
    +0.09
    0.08
    Negative Logits
    <bos>
    -2.99
    <?
    -1.11
    ⓧ
    -1.03
    /**
    -0.97
    /*
    -0.96
    
    -0.95
    /***
    -0.76
    #
    -0.71
    /*!
    -0.67
    #![
    -0.67
    POSITIVE LOGITS
     saar
    1.86
     lele
    1.77
     jaya
    1.77
     maksi
    1.73
     Græ
    1.73
     kasa
    1.67
     Juf
    1.66
     Præ
    1.65
     Minang
    1.65
     saha
    1.62
    Activations Density 0.773%

    No Known Activations