© 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-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 13950
    Prev
    Next
    INDEX
    Explanations

    references to historical context and narrative associated with certain events or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.81
    styleType
    -0.71
    Hozzáférés
    -0.66
    ngOnDestroy
    -0.61
    XMLSchema
    -0.59
    jsonwebtoken
    -0.59
    endmodule
    -0.59
    WriteLiteral
    -0.59
    ientôt
    -0.58
    ientí
    -0.58
    POSITIVE LOGITS
     history
    2.10
    history
    1.79
    History
    1.67
     History
    1.66
     HISTORY
    1.55
     histories
    1.51
    HISTORY
    1.41
     historia
    1.38
     sejarah
    1.37
     geschiedenis
    1.36
    Activations Density 0.371%

    No Known Activations