© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 352
    Prev
    Next
    INDEX
    Explanations

    markers of uncertainty or conditions in discussions or statements

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

    punctuation and transitional phrases in a context that implies a shift in thought or emphasis

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

    pronouns after punctuation or conjunctions

    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
    CppCodeGen
    -0.66
     AnyObject
    -0.50
    ếc
    -0.49
     moim
    -0.49
    elemField
    -0.49
    endpush
    -0.48
    ArrowToggle
    -0.47
    modb
    -0.47
    rode
    -0.45
    bewerken
    -0.43
    POSITIVE LOGITS
     they
    0.86
     you
    0.82
     we
    0.78
    They
    0.64
     EconPapers
    0.63
    onomía
    0.61
    you
    0.61
     YOU
    0.61
    We
    0.60
    COUVER
    0.60
    Activations Density 0.053%

    No Known Activations