© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 84720
    Prev
    Next
    INDEX
    Explanations

    terms related to emergency medical procedures and treatment logistics

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

    abstract concepts and states

    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
     évolu
    -0.34
     pagkak
    -0.31
     international
    -0.29
     and
    -0.29
     occhi
    -0.29
     thanks
    -0.28
     africaine
    -0.28
     méta
    -0.28
     czer
    -0.28
     exchange
    -0.28
    POSITIVE LOGITS
    estacks
    0.76
     ویکی‌پدی
    0.76
     אלא
    0.68
     المعيارى
    0.67
     resourceCulture
    0.67
    Personensuche
    0.67
    ChildScrollView
    0.66
     iNdEx
    0.65
    zzleHttp
    0.65
    DispatchToProps
    0.64
    Activations Density 0.569%

    No Known Activations