© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 15257
    Prev
    Next
    INDEX
    Explanations

    dialogues and interactions between characters in a narrative

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

    Action following dialogue or narration

    np_acts-logits-general · gemini-2.0-flash

    actions following pronouns or conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.70
    NameInMap
    -0.69
     AssemblyCulture
    -0.66
     cóc
    -0.63
     muualla
    -0.59
    PreferredItem
    -0.59
     goûts
    -0.58
     bezoek
    -0.58
    oplayer
    -0.56
    ftagPool
    -0.54
    POSITIVE LOGITS
     gest
    0.80
     stood
    0.79
     walked
    0.79
     strode
    0.77
     stepped
    0.76
     nodded
    0.75
     smiled
    0.73
     standing
    0.72
     pointing
    0.71
     walks
    0.71
    Activations Density 0.225%

    No Known Activations