© 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. 380
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating ability or possibility

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

    conditional phrases related to helping, capability, and future actions

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

    will / i'll + verb

    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
    aarrggbb
    -0.96
    참고
    -0.72
     تانيه
    -0.71
    @[+][
    -0.66
     Efq
    -0.66
    ThroughAttribute
    -0.65
    bibfield
    -0.63
     שוליים
    -0.63
     itſelf
    -0.62
     postIndex
    -0.61
    POSITIVE LOGITS
    Lähteet
    0.51
     give
    0.50
     guess
    0.48
     contactez
    0.47
    这就
    0.47
    setViewportView
    0.46
     Give
    0.46
    setLayoutManager
    0.46
    culate
    0.45
     gladly
    0.45
    Activations Density 0.042%

    No Known Activations