© 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. 38-GEMMASCOPE-RES-16K
    11. 7189
    Prev
    Next
    INDEX
    Explanations

    questions and explanations related to programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Artículos
    -0.78
    DEPORTES
    -0.78
     Masyarakat
    -0.77
     Lingkungan
    -0.72
     Infór
    -0.71
    Diámetro
    -0.71
     Garantía
    -0.69
     Komunikasi
    -0.69
     Keuangan
    -0.69
    majánló
    -0.68
    POSITIVE LOGITS
     endfor
    0.53
     $("<
    0.47
     newList
    0.45
     zufolge
    0.43
     Con
    0.43
     ervan
    0.42
     Com
    0.42
     Cu
    0.42
     $('<
    0.40
     maxHeight
    0.40
    Activations Density 0.076%

    No Known Activations