© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 117444
    Prev
    Next
    INDEX
    Explanations

    words and terms related to gold or gold-like substances

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

    "au" or "Au" followed by various endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Grüsse
    -0.67
     endroit
    -0.56
    endregion
    -0.56
    Cordialement
    -0.55
     lequel
    -0.49
    ItemIndex
    -0.48
     propOrder
    -0.47
     idea
    -0.47
    NodeName
    -0.46
     doigt
    -0.46
    POSITIVE LOGITS
    au
    0.99
    Au
    0.84
     Au
    0.80
    AU
    0.78
     Vau
    0.75
    Aura
    0.73
     Sau
    0.70
     AUR
    0.69
    wau
    0.69
     Auer
    0.68
    Activations Density 0.059%

    No Known Activations