© 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. 5063
    Prev
    Next
    INDEX
    Explanations

    features related to file storage and document collaboration in software applications

    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
    +0.34
    1.4%
    1842
    +0.22
    0.9%
    1403
    +0.16
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1403
    +0.34
    0.04
    678
    +0.22
    0.08
    1842
    +0.16
    0.04
    Negative Logits
    <bos>
    -2.33
    /***
    -0.86
    ⓧ
    -0.77
     conferir
    -0.73
    /**
    -0.72
     tentar
    -0.70
    ///**
    -0.69
     lutar
    -0.69
    amaño
    -0.69
     aceitar
    -0.65
    POSITIVE LOGITS
     lele
    1.15
     labd
    1.01
     ananas
    1.00
     alpes
    0.98
     maroc
    0.92
     milano
    0.89
     bont
    0.87
     siena
    0.87
     stik
    0.86
     bandung
    0.84
    Activations Density 0.865%

    No Known Activations