© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 13273
    Prev
    Next
    INDEX
    Explanations

    numerical and symbolic data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.53
    styleType
    -0.53
     Photocase
    -0.51
     <>",
    -0.49
     Мексичка
    -0.44
     &___
    -0.44
    httphttps
    -0.43
    orianCalendar
    -0.43
    RRect
    -0.43
     /*#__
    -0.42
    POSITIVE LOGITS
    angerie
    0.49
     مشين
    0.45
    TintMode
    0.41
    PerformLayout
    0.40
    клопе
    0.39
    Sklici
    0.39
    sendRedirect
    0.38
    versial
    0.38
     Schluß
    0.37
    endwhile
    0.37
    Activations Density 0.354%

    No Known Activations