© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 13569
    Prev
    Next
    INDEX
    Explanations

    questions and responses related to personal information and identification

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     BoxDecoration
    -0.39
     BorderSide
    -0.35
    sizeCache
    -0.31
    styleType
    -0.28
    ftagPool
    -0.28
     Chwiliwch
    -0.28
    ptăm
    -0.28
     habet
    -0.28
    GIVEREF
    -0.27
     externi
    -0.27
    POSITIVE LOGITS
     David
    1.29
     Michael
    1.29
     Andrew
    1.27
     Daniel
    1.25
     Kevin
    1.24
     Robert
    1.23
     Jennifer
    1.23
     John
    1.23
     Richard
    1.23
     Sarah
    1.23
    Activations Density 7.743%

    No Known Activations