© 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. 16-GEMMASCOPE-RES-16K
    11. 7883
    Prev
    Next
    INDEX
    Explanations

    negative phrases or sentiments about action or belief

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

    Contractions with "t" following an auxiliary verb

    np_acts-logits-general · gemini-2.0-flash

    don't know or want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Swift
    -0.61
    ing
    -0.56
    InSeconds
    -0.56
    PAGER
    -0.52
     órdenes
    -0.49
     hran
    -0.48
     hår
    -0.47
     Swift
    -0.47
     суб
    -0.47
    věř
    -0.47
    POSITIVE LOGITS
     have
    0.95
     need
    0.90
     ModelExpression
    0.88
    addGap
    0.84
     know
    0.82
    ftagPool
    0.82
    $")
    0.79
     believe
    0.79
     take
    0.78
     want
    0.78
    Activations Density 0.157%

    No Known Activations