© 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. 128590
    Prev
    Next
    INDEX
    Explanations

    references to bestselling personal development books and their related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    start of a code block

    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
    Not in Any Lists

    No Comments

    Negative Logits
    glGen
    -0.30
    Fatalf
    -0.30
     Füße
    -0.29
     recepción
    -0.27
    VersionUID
    -0.26
     وحد
    -0.25
    xfe
    -0.25
    $_['
    -0.25
     meri
    -0.24
     cuna
    -0.24
    POSITIVE LOGITS
     StringTokenizer
    0.71
    Jeografia
    0.66
     متعلقه
    0.63
    imageshack
    0.60
     disambiguazione
    0.56
    tangentMode
    0.55
     endregion
    0.55
    IntoConstraints
    0.54
    ighted
    0.54
    GroupLayout
    0.51
    Activations Density 0.036%

    No Known Activations