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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 55941
    Prev
    Next
    INDEX
    Explanations

    medical and health-related terminology, particularly focusing on conditions, treatments, and risks

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

    prevention and relief

    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
     Schwier
    -0.36
     Lleg
    -0.36
     halben
    -0.35
     Aussch
    -0.34
     vuestros
    -0.34
    
    -0.34
    Enllaces
    -0.33
     Koffer
    -0.33
     yürü
    -0.33
     llev
    -0.32
    POSITIVE LOGITS
     protection
    0.60
     prevention
    0.58
    jenost
    0.58
     PTC
    0.56
     Protection
    0.56
    WireFormat
    0.55
    chaikovsky
    0.54
     Prevention
    0.54
    bindingNavigator
    0.54
     Viro
    0.54
    Activations Density 0.045%

    No Known Activations