© 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. 20-GEMMASCOPE-RES-16K
    11. 6946
    Prev
    Next
    INDEX
    Explanations

    instances of performing or appearing on stage

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

    stages, fields, and stadiums

    np_acts-logits-general · gemini-2.0-flash

    performance and sports venues

    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
    aarrggbb
    -0.91
    SharedCtor
    -0.71
    PreExecute
    -0.65
    PreferredItem
    -0.65
    SharedDtor
    -0.63
    sizeCache
    -0.61
    ortment
    -0.60
    ChildScrollView
    -0.60
     typelib
    -0.59
    RTDA
    -0.58
    POSITIVE LOGITS
     stage
    1.89
    stage
    1.54
     onstage
    1.47
     Stage
    1.33
     STAGE
    1.30
     stages
    1.28
    Stage
    1.26
    STAGE
    1.21
     Bühne
    1.19
     palco
    1.12
    Activations Density 0.129%

    No Known Activations