© 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. 31-GEMMASCOPE-RES-16K
    11. 3023
    Prev
    Next
    INDEX
    Explanations

    references to books, publishers, and academic institutions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    bibliographic citations and publication information in parentheses.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     cortinas
    -0.36
     nahilalakip
    -0.34
    adpleegd
    -0.33
     mukaan
    -0.32
    更何况
    -0.30
     Anlage
    -0.30
    isière
    -0.30
     Oncol
    -0.29
     tým
    -0.29
     متعلقه
    -0.29
    POSITIVE LOGITS
     publisher
    1.40
     publishers
    1.35
     publishing
    1.30
     Publisher
    1.13
     Publishing
    1.10
    publisher
    1.08
     Publishers
    1.07
     PUBLISH
    1.05
    publish
    1.04
    PUBLISH
    1.04
    Activations Density 0.272%

    No Known Activations