© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7073
    Prev
    Next
    INDEX
    Explanations

    phrases related to clear communication and guidance

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

    providing guidance or instructions

    np_acts-logits-general · gemini-2.0-flash

    advice, recommendations, and guides

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions of guidance or instructional resources (documentation, tutorials, help/support content, books) indicating learning or advice-oriented material.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    kwds
    -0.42
     calculées
    -0.30
     interrog
    -0.29
     avven
    -0.28
     tilf
    -0.28
     manifest
    -0.28
    Leistungs
    -0.27
    lihatkan
    -0.26
    toHaveBeen
    -0.26
    レーキ
    -0.26
    POSITIVE LOGITS
     advices
    0.78
     advice
    0.78
    featureID
    0.75
    advice
    0.71
     ADVICE
    0.70
     recommendations
    0.69
    recommendations
    0.68
     guides
    0.66
     guidance
    0.66
    Consejos
    0.66
    Activations Density 0.472%

    No Known Activations