© 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. 4466
    Prev
    Next
    INDEX
    Explanations

    references to specific years or times

    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
    +0.19
    0.7%
    776
    +0.14
    0.5%
    678
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.19
    0.05
    1376
    +0.14
    0.04
    499
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.46
    例文帳に追加
    -0.71
    ,
    -0.69
    ;
    -0.69
    .
    -0.67
     saites
    -0.64
     uska
    -0.64
    ništvo
    -0.63
     for
    -0.62
     мәгълү
    -0.62
    POSITIVE LOGITS
     emphat
    2.23
     reluct
    2.22
     accla
    2.17
     maneu
    2.15
     disagre
    2.14
     affor
    2.10
     increa
    2.09
     shenan
    2.09
     impra
    2.06
     inev
    2.04
    Activations Density 0.120%

    No Known Activations