© 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 EvalsExportsinterp-engineNEWAPI 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. 53530
    Prev
    Next
    INDEX
    Explanations

    terms related to injuries and wounds

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

    wounded, wounding, wounds

    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
     Autorizaciones
    -0.54
    XAxis
    -0.48
     Autorisations
    -0.46
    pruch
    -0.46
    seteq
    -0.46
     Cik
    -0.45
     arrangement
    -0.45
    regeln
    -0.44
     useRouter
    -0.44
    izedBox
    -0.44
    POSITIVE LOGITS
     wounded
    1.74
     Wounded
    1.59
     wounding
    1.16
     blessé
    1.02
     blessés
    0.93
     herido
    0.92
     heridos
    0.88
     wounds
    0.75
     injured
    0.74
     Wounds
    0.72
    Activations Density 0.005%

    No Known Activations