© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7517
    Prev
    Next
    INDEX
    Explanations

    references to recipes and culinary instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     “
    -0.56
    hover
    -0.54
     Hover
    -0.53
    awareness
    -0.48
      
    -0.48
    Hover
    -0.47
     Payne
    -0.47
     Poy
    -0.47
    aware
    -0.47
     Awareness
    -0.46
    POSITIVE LOGITS
     recipe
    0.97
     RECIPE
    0.82
    Recipe
    0.78
     recipes
    0.76
    recipe
    0.75
     NSCoder
    0.73
     Recipe
    0.73
     receta
    0.71
     Recipes
    0.67
     recette
    0.64
    Activations Density 0.191%

    No Known Activations