© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10031
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions involving derivatives, integrals, and algebraic calculations

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

    mathematical operators in equations, particularly plus and minus signs.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]){
    -0.28
     humble
    -0.28
     laid
    -0.27
     lain
    -0.25
    }{{
    -0.25
    cshtml
    -0.24
     Polda
    -0.24
    stasia
    -0.24
     Polsek
    -0.24
     Pon
    -0.24
    POSITIVE LOGITS
    Personensuche
    0.79
     فريبيس
    0.77
    Portály
    0.77
     समीक्षाओं
    0.77
     Italijani
    0.77
     Италијани
    0.76
     Administrativna
    0.72
    цездатний
    0.71
    AndEndTag
    0.71
     referenties
    0.71
    Activations Density 0.681%

    No Known Activations