© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 403
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions, specifically focusing on surgical procedures and anatomical details

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "head" or "headache"

    np_acts-logits-general · gemini-2.0-flash

    head injury or surgery

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Negative Logits
     lenker
    -0.50
    出版年
    -0.44
    BagConstraints
    -0.43
     Réponses
    -0.43
    itinéraire
    -0.42
    schedulers
    -0.42
    borderFill
    -0.41
     wireType
    -0.41
    reactstrap
    -0.40
    Schedulers
    -0.40
    POSITIVE LOGITS
     scalp
    0.64
     helmets
    0.61
     skull
    0.60
     helmet
    0.57
     casque
    0.54
    cipital
    0.54
     Helmet
    0.52
     kepala
    0.52
     head
    0.51
     skulls
    0.50
    Activations Density 0.378%

    No Known Activations