© 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. 6209
    Prev
    Next
    INDEX
    Explanations

    references to indices or indexing structures in code or data

    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
    UserScript
    -0.57
    ฒ
    -0.44
     bVar
    -0.44
    toHaveBeenCalled
    -0.43
    Camila
    -0.43
    reau
    -0.43
     gdyby
    -0.40
     Camila
    -0.40
    Svc
    -0.40
    camel
    -0.40
    POSITIVE LOGITS
     Index
    1.22
     index
    1.18
    Index
    1.12
     INDEX
    1.09
    index
    1.04
    getIndex
    1.04
    INDEX
    0.98
     getIndex
    0.92
     indexes
    0.90
     Indexing
    0.87
    Activations Density 0.167%

    No Known Activations