© 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. 22-GEMMASCOPE-RES-16K
    11. 14187
    Prev
    Next
    INDEX
    Explanations

    technical descriptions related to lighting technology, specifically compact fluorescent lamps and their innovations

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

    Lighting and light-related equipment

    np_acts-logits-general · gemini-2.0-flash

    lighting and lamps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.57
     &___
    -0.49
    UVWXYZ
    -0.49
     CARTOON
    -0.48
    cocks
    -0.47
    antine
    -0.47
     Hear
    -0.46
    endregion
    -0.46
    kloped
    -0.46
     Администра
    -0.46
    POSITIVE LOGITS
     fixture
    0.83
     CRI
    0.78
    Fixture
    0.73
     fixtures
    0.72
     Fixture
    0.72
    fixtures
    0.70
     dimming
    0.69
    fixture
    0.68
    CRI
    0.67
     Fixtures
    0.66
    Activations Density 0.161%

    No Known Activations