© 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 - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 2183
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare and patient management in medical contexts

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

    inpatient psychiatric secure care facilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    interopRequire
    -0.38
    TableBody
    -0.35
    tigkeits
    -0.33
    verzeichnis
    -0.32
    ListItemIcon
    -0.32
    UpInside
    -0.31
     '\\;'
    -0.31
    oplasts
    -0.31
    ActionCreators
    -0.30
    CardContent
    -0.30
    POSITIVE LOGITS
     acute
    0.77
     inpatient
    0.70
    急性
    0.69
     Acute
    0.68
    Acute
    0.67
    acute
    0.64
     specialized
    0.60
     stabilization
    0.57
     purpoſe
    0.56
     seclusion
    0.56
    Activations Density 0.059%

    No Known Activations