© 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. 4873
    Prev
    Next
    INDEX
    Explanations

    instances of numerical data or counts

    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
    +0.31
    1.6%
    1343
    +0.16
    0.8%
    1967
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.31
    0.04
    562
    +0.16
    0.04
    924
    +0.13
    0.04
    Negative Logits
    <bos>
    -2.95
    ⓧ
    -1.28
    /**
    -1.24
    
    -1.04
     intersper
    -0.99
    <?
    -0.97
     quitted
    -0.90
     forbear
    -0.90
    /***
    -0.89
    /*
    -0.88
    POSITIVE LOGITS
     seksi
    0.86
     corrom
    0.75
     cooperativa
    0.73
     maksi
    0.72
     grossa
    0.71
     marea
    0.71
     Teknik
    0.71
     Fakta
    0.70
     geografia
    0.69
     marte
    0.69
    Activations Density 0.045%

    No Known Activations