© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 3007
    Prev
    Next
    INDEX
    Explanations

    terms related to health interventions and their evaluations

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

    after tokens ending with "ion"

    np_acts-logits-general · gemini-2.0-flash

    analysis and visualisation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.68
    ContentAsync
    -0.67
     clove
    -0.66
     caviar
    -0.66
     handker
    -0.65
    esgue
    -0.64
     AppModule
    -0.63
     cohomology
    -0.62
     rivets
    -0.62
     HST
    -0.62
    POSITIVE LOGITS
     سكانية
    0.59
    исленность
    0.59
     الاطلاع
    0.54
     Chwiliwch
    0.46
     становника
    0.44
    клопе
    0.44
    Hozzáférés
    0.44
    ிகள்
    0.44
     Vikipedi
    0.43
     العنوان
    0.43
    Activations Density 0.424%

    No Known Activations