© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 55043
    Prev
    Next
    INDEX
    Explanations

    parentheses and package declarations in code

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

    Go package declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Infór
    -0.40
    États
    -0.39
    queryInterface
    -0.37
     jugement
    -0.35
     hacia
    -0.35
     bénéfice
    -0.35
    HMIS
    -0.34
     seyn
    -0.33
     þat
    -0.33
     quedado
    -0.32
    POSITIVE LOGITS
    package
    2.36
     package
    1.52
     Package
    1.41
     packages
    1.34
    Package
    1.34
     PACKAGE
    1.26
     Packages
    1.26
    PACKAGE
    1.21
    packages
    1.05
    パッケージ
    1.04
    Activations Density 0.000%

    No Known Activations