© 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. 20-GEMMASCOPE-RES-16K
    11. 1270
    Prev
    Next
    INDEX
    Explanations

    restaurant-related phrases, particularly around meal courses and ordering etiquette

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

    meals and courses

    np_acts-logits-general · gemini-2.0-flash

    meal course types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     CreateTagHelper
    -0.90
     ModelExpression
    -0.79
    HtmlAttribute
    -0.77
    WithIOException
    -0.70
     PopupWindow
    -0.61
    '])->
    -0.61
    Tembelea
    -0.59
    IntoConstraints
    -0.59
     jsPsych
    -0.59
     AssemblyCulture
    -0.58
    POSITIVE LOGITS
     starters
    1.20
     courses
    1.16
     appetizer
    1.15
     course
    1.13
     appetizers
    1.12
     starter
    1.10
     dessert
    1.03
     entree
    0.97
     entrée
    0.96
     Course
    0.94
    Activations Density 0.134%

    No Known Activations