© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 11204
    Prev
    Next
    INDEX
    Explanations

    phrases related to divisions and classifications

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

    "Division" or "Div"

    np_acts-logits-general · gemini-2.0-flash

    division or divis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lccn
    -0.76
     disponibilités
    -0.74
     resourceCulture
    -0.67
     CreateTagHelper
    -0.67
     complètes
    -0.60
    DeleteBehavior
    -0.60
    invokeLater
    -0.59
    AtIndexPath
    -0.59
    intellij
    -0.58
    noscript
    -0.56
    POSITIVE LOGITS
     division
    0.93
     DIV
    0.89
     divis
    0.88
     divisions
    0.87
     Div
    0.84
     divider
    0.84
     partition
    0.84
     DIVISION
    0.82
     Divisions
    0.81
     Division
    0.79
    Activations Density 0.258%

    No Known Activations