© 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. 6238
    Prev
    Next
    INDEX
    Explanations

    mathematical constructs and symbols

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

    mathematical or programming syntax, specifically LaTeX matrix notation and code structures with indices and coordinate systems.

    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
    IndentedString
    -0.67
    matchCondition
    -0.57
     $_(
    -0.56
    NameInMap
    -0.56
     autorytatywna
    -0.56
     насељу
    -0.56
     ſche
    -0.55
     パンチラ
    -0.54
    <unused43>
    -0.54
     好文分享
    -0.54
    POSITIVE LOGITS
     actualidad
    0.48
     templado
    0.45
    occasione
    0.44
     overras
    0.43
     ausencia
    0.41
     reducido
    0.40
     vastaan
    0.40
     temprana
    0.39
    corrência
    0.39
    empêcher
    0.39
    Activations Density 0.518%

    No Known Activations