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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16275
    Prev
    Next
    INDEX
    Explanations

    phrases or elements related to user engagement and interaction with content or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follow up requests or confirmations

    np_acts-logits-general · gemini-2.0-flash

    Please, next, confirmation, hope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.75
    IntoConstraints
    -0.73
     Italijanski
    -0.68
     ſind
    -0.68
    :✨
    -0.68
     ModelExpression
    -0.67
    ésultats
    -0.67
    ScopeManager
    -0.67
     BorderSide
    -0.66
    Rhestr
    -0.63
    POSITIVE LOGITS
    rus
    0.38
    Please
    0.35
     detailed
    0.35
    detailed
    0.34
     te
    0.33
    NEXT
    0.33
    Next
    0.33
     Please
    0.32
     Next
    0.32
    希望
    0.32
    Activations Density 0.171%

    No Known Activations