© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 76377
    Prev
    Next
    INDEX
    Explanations

    references to acute medical conditions or acute phases of illnesses

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

    acute medical conditions

    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
     impresora
    -0.52
     éditoriale
    -0.48
     naudo
    -0.45
     équilibr
    -0.43
    makaian
    -0.43
     Parson
    -0.43
     noastră
    -0.43
    orden
    -0.43
     écou
    -0.43
     scientifiques
    -0.42
    POSITIVE LOGITS
     acute
    2.06
    Acute
    1.98
     Acute
    1.95
    acute
    1.64
     acutely
    1.43
     akut
    1.32
    急性
    1.23
     aguda
    1.03
     aigu
    0.95
     acuity
    0.87
    Activations Density 0.005%

    No Known Activations