© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2617
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to molecular structures and processes

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

    scientific/technical research terminology and descriptions of protein structures and molecular analysis techniques.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    technical terms related to molecular biology, biochemistry, and protein structures.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     situation
    -0.35
     day
    -0.31
     name
    -0.30
     since
    -0.30
     because
    -0.29
     Multi
    -0.29
     election
    -0.28
     check
    -0.27
     date
    -0.26
     won
    -0.26
    POSITIVE LOGITS
     مشين
    0.87
    sidemargin
    0.74
     PicClick
    0.71
    出版年
    0.69
     wireType
    0.69
    ſicht
    0.69
    parsedMessage
    0.68
     незавершена
    0.68
    writeFieldEnd
    0.68
     disambiguazione
    0.67
    Activations Density 1.070%

    No Known Activations