Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Post
    5. 12-GEMMASCOPE-RES-1M
    6. 375
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations typically used in equations and formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.70
    ]='\
    -0.55
    IntoConstraints
    -0.55
     CGPoint
    -0.55
    GenerationType
    -0.54
    enderror
    -0.54
    Abitanti
    -0.52
     Hamb
    -0.52
    lho
    -0.50
    OutOfRange
    -0.50
    POSITIVE LOGITS
     ویکی‌پدیا
    0.64
     المعيارى
    0.64
     Roskov
    0.53
    setVerticalGroup
    0.52
    ksikon
    0.51
     GeoNames
    0.50
     oprot
    0.47
     ويكيميديا
    0.47
     NUKAT
    0.47
     فريبيس
    0.46
    Activations Density 0.083%

    No Known Activations