© 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. 19-GEMMASCOPE-RES-16K
    11. 101
    Prev
    Next
    INDEX
    Explanations

    strings or sequences that represent identifiers or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.79
    EFIAPI
    -0.72
    ReusableCell
    -0.69
     kaarangay
    -0.67
    msgTypes
    -0.65
     ModelExpression
    -0.65
    parsedMessage
    -0.65
    Hauptartikel
    -0.64
     дописавши
    -0.63
    sulf
    -0.62
    POSITIVE LOGITS
    c
    0.85
    l
    0.69
    f
    0.68
    b
    0.64
    in
    0.60
    v
    0.58
     ejus
    0.58
    p
    0.57
    Step
    0.53
    g
    0.53
    Activations Density 0.136%

    No Known Activations