© 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. 15-GEMMASCOPE-RES-16K
    11. 1276
    Prev
    Next
    INDEX
    Explanations

    mathematical or programming symbols and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createState
    -0.61
    WarningLevel
    -0.45
     perfection
    -0.45
     flan
    -0.44
    gos
    -0.43
     Gulch
    -0.42
     faint
    -0.42
     상세
    -0.42
    komend
    -0.41
     Gaspar
    -0.41
    POSITIVE LOGITS
    :✨
    0.93
    TintMode
    0.72
    ScopeManager
    0.71
    تقاوى
    0.69
    APORE
    0.69
     Италијани
    0.67
    AndView
    0.65
    الحياه
    0.64
     <=",
    0.62
    ImageContext
    0.62
    Activations Density 1.064%

    No Known Activations