© 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. 23-GEMMASCOPE-RES-16K
    11. 12311
    Prev
    Next
    INDEX
    Explanations

    specific references to documents or records with significant content

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    parsedMessage
    -0.73
     للاسماء
    -0.57
    InjectAttribute
    -0.57
    StructEnd
    -0.53
    énario
    -0.45
     ziekte
    -0.45
    AutoScale
    -0.44
    CloseOperation
    -0.44
    shmi
    -0.44
     ainfi
    -0.43
    POSITIVE LOGITS
     THOSE
    0.52
     THAT
    0.49
     those
    0.46
    Those
    0.45
    JAKARTA
    0.45
     thats
    0.44
     Those
    0.43
     That
    0.43
     esas
    0.43
    That
    0.42
    Activations Density 0.373%

    No Known Activations