© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14258
    Prev
    Next
    INDEX
    Explanations

    descriptions of medical conditions and research developments related to drug treatments

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

    appearing in research papers or documentation

    np_acts-logits-general · gemini-2.0-flash

    recent developments and results

    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
    contentLoaded
    -0.98
    featureID
    -0.91
    LookAnd
    -0.88
     tartalomajánló
    -0.84
     للاسماء
    -0.82
     typelib
    -0.77
    XmlAccessorType
    -0.77
    RenderAtEndOf
    -0.70
    Tikang
    -0.70
     ویکی‌پدی
    -0.70
    POSITIVE LOGITS
     recent
    0.38
     latest
    0.34
     Recent
    0.31
    【
    0.31
    <em>
    0.30
     recente
    0.30
    最新
    0.29
     operations
    0.29
    ・
    0.29
    latest
    0.28
    Activations Density 0.353%

    No Known Activations