© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 11687
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their contextual usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.80
     isNameExpr
    -0.61
    InjectAttribute
    -0.59
     مرئيه
    -0.58
    $_['
    -0.58
    rungsseite
    -0.58
    ⎊
    -0.57
     esternos
    -0.56
     uska
    -0.56
     Wicidata
    -0.56
    POSITIVE LOGITS
     thereby
    1.07
     making
    0.94
     thus
    0.94
     allowing
    0.85
     giving
    0.85
     ensuring
    0.81
     prompting
    0.77
     enabling
    0.76
     leaving
    0.75
     resulting
    0.75
    Activations Density 1.088%

    No Known Activations