© 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. 16-GEMMASCOPE-RES-16K
    11. 9331
    Prev
    Next
    INDEX
    Explanations

    references to ingredients and their quantities in recipes

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

    Parts, components, or ingredients

    np_acts-logits-general · gemini-2.0-flash

    individual components or ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Battista
    -0.60
     handker
    -0.52
    ThemeOverlay
    -0.52
    afficheront
    -0.51
    UpInside
    -0.51
    utches
    -0.49
    êques
    -0.48
     craters
    -0.48
     tailgate
    -0.48
    gama
    -0.47
    POSITIVE LOGITS
     components
    0.95
     composants
    0.83
     items
    0.81
     component
    0.79
     componentes
    0.75
     ingredients
    0.73
    components
    0.71
     Components
    0.71
     komponen
    0.69
     Komponenten
    0.69
    Activations Density 0.556%

    No Known Activations