© 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. 11159
    Prev
    Next
    INDEX
    Explanations

    references to societal trends and challenges

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

    Prepositions or words that can act as prepositions

    np_acts-logits-general · gemini-2.0-flash

    limited knowledge about

    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
     ویکی‌پدی
    -0.82
     ModelExpression
    -0.75
     Италијани
    -0.67
    GTCX
    -0.66
    TemporalType
    -0.66
    CloseOperation
    -0.63
     tartalomajánló
    -0.63
     propOrder
    -0.61
     للاسماء
    -0.61
    setVerticalGroup
    -0.60
    POSITIVE LOGITS
    ich
    0.38
    Ser
    0.35
    sey
    0.35
    șe
    0.34
    Dest
    0.34
     Kurz
    0.34
    forChild
    0.34
    inty
    0.34
    rig
    0.32
    SRC
    0.32
    Activations Density 0.779%

    No Known Activations