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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 12748
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and quantitative expressions related to measurements and experimental data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.47
    endregion
    -0.36
    transQ
    -0.35
    subpackage
    -0.35
    ngdoc
    -0.35
    webElementXpaths
    -0.33
     geldig
    -0.32
     itinéraires
    -0.32
    gnore
    -0.31
    Kariera
    -0.31
    POSITIVE LOGITS
     (+
    1.68
     $+
    1.63
    ,+
    1.61
    =+
    1.55
     +
    1.54
    (+
    1.52
    :+
    1.50
     [+
    1.44
    /+
    1.39
    +
    1.37
    Activations Density 0.825%

    No Known Activations