© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 4818
    Prev
    Next
    INDEX
    Explanations

    programming-related codes or commands for building modules, classes, and controllers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    453
    +0.14
    0.4%
    876
    +0.11
    0.3%
    599
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.14
    0.00
    453
    +0.11
    0.03
    1871
    +0.08
    0.02
    Negative Logits
    <bos>
    -1.02
    %。
    -0.63
     there
    -0.62
     of
    -0.62
     and
    -0.62
     to
    -0.61
     in
    -0.61
     due
    -0.60
     at
    -0.60
    URLException
    -0.60
    POSITIVE LOGITS
     peppa
    1.78
     scrat
    1.77
     affor
    1.74
     increa
    1.69
     coq
    1.63
     milf
    1.62
     guarante
    1.62
     ?...
    1.62
     wikihow
    1.62
     !...
    1.61
    Activations Density 0.125%

    No Known Activations