© 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. 20-GEMMASCOPE-RES-131K
    11. 69075
    Prev
    Next
    INDEX
    Explanations

    specific terms related to medical examinations and testing contexts

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

    examination table, test tube, cutting board, convention center

    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
    TagMode
    -0.65
     ModelExpression
    -0.61
     للاسماء
    -0.60
    ngdoc
    -0.57
    InjectAttribute
    -0.56
    Portale
    -0.54
    herself
    -0.53
    Hochspringen
    -0.52
    AxisAlignment
    -0.52
    kmale
    -0.52
    POSITIVE LOGITS
     tea
    0.49
     garden
    0.48
     dining
    0.45
     Skid
    0.45
     golf
    0.44
     Garden
    0.44
     shopping
    0.43
     aé
    0.42
     stor
    0.42
     dinner
    0.41
    Activations Density 0.241%

    No Known Activations