© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3606
    Prev
    Next
    INDEX
    Explanations

    information related to coding and software development, specifically looking for details about code size, code quality, and coding standards

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    876
    +0.20
    0.6%
    690
    +0.11
    0.3%
    344
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.20
    0.02
    441
    +0.11
    0.04
    872
    +0.11
    0.06
    Negative Logits
    <bos>
    -0.61
     Potosí
    -0.54
     Asunción
    -0.53
    Biografia
    -0.53
    Filmografia
    -0.52
     Jehová
    -0.51
    BackgroundImage
    -0.50
     Princesa
    -0.50
    헌
    -0.50
     Antônio
    -0.50
    POSITIVE LOGITS
     abnorm
    1.44
     effe
    1.35
     overla
    1.34
     pessi
    1.25
     inder
    1.22
     thut
    1.20
     mef
    1.19
     guarante
    1.19
     desir
    1.19
     fep
    1.18
    Activations Density 0.628%

    No Known Activations