© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4073
    Prev
    Next
    INDEX
    Explanations

    details about a person's career and achievements in sports

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.34
    1.4%
    381
    +0.15
    0.6%
    1177
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.34
    0.09
    513
    +0.15
    0.04
    1095
    +0.11
    0.04
    Negative Logits
    <bos>
    -2.23
    intios
    -0.70
    ///**
    -0.67
    addCriterion
    -0.66
    पया
    -0.65
     butterknife
    -0.63
    sizeCache
    -0.62
    PerformLayout
    -0.62
     abstra
    -0.61
    🎰
    -0.61
    POSITIVE LOGITS
     reluct
    1.82
     disagre
    1.80
     unspeak
    1.78
     apprehen
    1.72
     affor
    1.66
     maneu
    1.63
     increa
    1.59
     accla
    1.57
     indescri
    1.57
     gaily
    1.54
    Activations Density 0.382%

    No Known Activations