© 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. 3-GEMMASCOPE-RES-16K
    11. 8132
    Prev
    Next
    INDEX
    Explanations

    technical or mathematical terminology related to equations and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pushFollow
    -0.39
     consentimento
    -0.38
     colher
    -0.36
     générations
    -0.33
    makeConstraints
    -0.33
    󠁴
    -0.33
     surla
    -0.32
    ²/
    -0.32
     Connectez
    -0.32
     inconn
    -0.31
    POSITIVE LOGITS
    scriptsize
    0.67
    boldmath
    0.65
    textbf
    0.63
    ">//
    0.60
    :✨
    0.58
    Bbb
    0.57
    mathsf
    0.57
    mathscr
    0.56
    footnotesize
    0.55
    mathcal
    0.54
    Activations Density 0.660%

    No Known Activations