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

    Neuronpedia

    Jacobian LensNEW
    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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12328
    Prev
    Next
    INDEX
    Explanations

    sections that discuss editorial suggestions and modifications for clarity

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

    Requests for feedback, clarification, or suggestions

    np_acts-logits-general · gemini-2.0-flash

    user feedback and questions

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     استنادى
    -0.57
    舺
    -0.56
    writeFieldEnd
    -0.54
    ┛
    -0.52
    unger
    -0.51
     alak
    -0.51
     OFDb
    -0.49
     sorrows
    -0.49
    segno
    -0.48
     erſt
    -0.48
    POSITIVE LOGITS
    Erstellt
    0.42
    पया
    0.42
    :+:
    0.41
    DeleteBehavior
    0.41
     Infórmanos
    0.40
    httphttps
    0.39
    awtextra
    0.39
    migrationBuilder
    0.39
    DockStyle
    0.39
     désolés
    0.37
    Activations Density 1.514%

    No Known Activations