© 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. 461
    Prev
    Next
    INDEX
    Explanations

    programming and computational structures like functions, classes, and return statements

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

    code syntax elements like brackets, braces, and programming language-specific symbols.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
     Chip
    -0.45
     ex
    -0.42
    }}_{\
    -0.41
    setcounter
    -0.40
     Fra
    -0.39
     Mid
    -0.38
     Sy
    -0.37
     Stu
    -0.37
     Nom
    -0.37
     Split
    -0.37
    POSITIVE LOGITS
     plufieurs
    0.84
    :✨
    0.83
     Infór
    0.80
     ainfi
    0.79
    IUrlHelper
    0.78
    GEBURTSDATUM
    0.72
     kvä
    0.71
     regalías
    0.70
     increí
    0.69
    səhifə
    0.68
    Activations Density 0.388%

    No Known Activations