© 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. 16240
    Prev
    Next
    INDEX
    Explanations

    instances of sitting or the act of being seated

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

    "sit" and its variations

    np_acts-logits-general · gemini-2.0-flash

    sit and wait, sit down

    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
    GEBURTSDATUM
    -0.69
     Réponses
    -0.68
    })));
    -0.66
    numerusform
    -0.63
    ORPG
    -0.63
    migrationBuilder
    -0.61
    ConstraintMaker
    -0.60
     Италијани
    -0.60
     Meksiku
    -0.60
    ⋙
    -0.60
    POSITIVE LOGITS
     sit
    0.78
     idle
    0.77
    Sit
    0.73
     down
    0.72
     Sit
    0.68
     sits
    0.62
    sit
    0.61
     sitzen
    0.60
     sitting
    0.60
     idly
    0.58
    Activations Density 0.081%

    No Known Activations