© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 116972
    Prev
    Next
    INDEX
    Explanations

    references to figures and graphical representations in academic or technical documents

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

    referring to figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     médié
    -0.38
    了嗎
    -0.37
     saham
    -0.36
    商品説明
    -0.35
    árqu
    -0.34
    จัก
    -0.34
     maravillas
    -0.34
    latego
    -0.33
     Zeal
    -0.33
     вагі
    -0.32
    POSITIVE LOGITS
    figure
    2.52
     figure
    1.95
    figures
    1.52
     figures
    1.40
    Figure
    1.39
     Figure
    1.34
     figura
    1.34
     FIGURE
    1.30
    FIGURE
    1.29
    figura
    1.23
    Activations Density 0.054%

    No Known Activations