© 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 - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14701
    Prev
    Next
    INDEX
    Explanations

    commands and functions related to file and connection operations

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

    Ending or closing actions

    np_acts-logits-general · gemini-2.0-flash

    stopping or concluding actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Réponses
    -0.56
    ArgsConstructor
    -0.54
     PartialEq
    -0.50
    APORE
    -0.48
     שוליים
    -0.48
    msford
    -0.47
     HasFactory
    -0.46
    dized
    -0.46
    󠁢
    -0.46
    typeparam
    -0.46
    POSITIVE LOGITS
     gracefully
    0.76
    WithError
    0.69
     cleanly
    0.63
    immediately
    0.59
     abruptly
    0.59
    AfterClass
    0.58
     prematurely
    0.58
    Requested
    0.57
    RenderAtEndOf
    0.56
    Immediately
    0.56
    Activations Density 0.249%

    No Known Activations