© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 479
    Prev
    Next
    INDEX
    Explanations

    references to congressional processes and government-related topics

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

    references to legislative sessions and administrative communications

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

    conjunctions and prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Kon
    -1.40
     kon
    -1.40
    Kon
    -1.38
     CON
    -1.36
    CON
    -1.34
     Кон
    -1.34
    Кон
    -1.34
     Conrad
    -1.33
     Conc
    -1.32
    skon
    -1.31
    POSITIVE LOGITS
    isseurs
    0.49
    woordig
    0.45
    تهى
    0.43
     amico
    0.42
    memoized
    0.41
    jako
    0.40
     adaptées
    0.40
     cherchez
    0.40
    役所
    0.39
     mezzi
    0.39
    Activations Density 0.112%

    No Known Activations