© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 15797
    Prev
    Next
    INDEX
    Explanations

    the start of sections or passages in a document, denoted by the "<bos>" token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iligung
    -0.54
    NewValue
    -0.51
     trending
    -0.48
     particular
    -0.48
    ículos
    -0.47
     Murch
    -0.47
     Elie
    -0.47
    ueva
    -0.47
     Total
    -0.47
    TERN
    -0.46
    POSITIVE LOGITS
    InjectAttribute
    1.03
    Билгалдахарш
    0.92
    Datuak
    0.86
    webElementXpaths
    0.84
     '\\;'
    0.84
    LookAnd
    0.80
    ViewImports
    0.79
    @[+][
    0.78
     ویکی‌پدیای
    0.78
    UnsafeEnabled
    0.77
    Activations Density 0.038%

    No Known Activations