© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14427
    Prev
    Next
    INDEX
    Explanations

    descriptions of restaurant menus and food offerings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.70
     Rosen
    -0.52
     geme
    -0.45
     Production
    -0.45
    erom
    -0.42
    रीद
    -0.42
     нар
    -0.42
    SharedDtor
    -0.41
    Production
    -0.40
     Distribute
    -0.40
    POSITIVE LOGITS
     dish
    1.24
     dishes
    1.23
     Dish
    0.89
     Dishes
    0.86
     recipes
    0.86
    Dish
    0.85
     piatti
    0.81
     DISH
    0.81
    Dishes
    0.81
     entree
    0.79
    Activations Density 0.165%

    No Known Activations