© 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. 31-GEMMASCOPE-RES-131K
    11. 2311
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to programming and computational models

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

    as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    rungsseite
    -0.61
     linkovi
    -0.52
     Monfieur
    -0.51
     Anſ
    -0.50
     indígen
    -0.49
    蚪
    -0.49
    ſelf
    -0.49
    OGND
    -0.48
     المعيارى
    -0.48
     Houſe
    -0.47
    POSITIVE LOGITS
     sebagai
    1.96
    作为
    1.75
     as
    1.67
    作為
    1.61
     jako
    1.49
    sebagai
    1.48
     Sebagai
    1.45
     ως
    1.36
     به‌عنوان
    1.29
    作为一个
    1.29
    Activations Density 0.557%

    No Known Activations