© 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. 8144
    Prev
    Next
    INDEX
    Explanations

    names of people or entities associated with specific contexts or citations

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

    Tokens before bracketed citations

    np_acts-logits-general · gemini-2.0-flash

    Bonheur, Bonnet, Binet, Binns

    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
     Spisak
    -0.68
    titleMargin
    -0.64
    ItemBackground
    -0.63
     transférez
    -0.62
     Theſe
    -0.59
     trasladado
    -0.57
    {}{}
    -0.57
    })).
    -0.56
    ać
    -0.55
    WithIOException
    -0.55
    POSITIVE LOGITS
     StatefulWidget
    0.77
    PhysRevD
    0.54
     StatelessWidget
    0.53
    ⓧ
    0.52
     Gen
    0.51
    tvguidetime
    0.50
    IActionResult
    0.48
    Gen
    0.47
    dim
    0.47
    Билгалдахарш
    0.46
    Activations Density 0.150%

    No Known Activations