© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8878
    Prev
    Next
    INDEX
    Explanations

    phrases indicating legal or organizational entities

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

    Follows "of" and is a location or field of study

    np_acts-logits-general · gemini-2.0-flash

    country, organization, or field names

    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
    daki
    -0.47
    jangan
    -0.47
     così
    -0.46
     محفوظة
    -0.45
    目
    -0.44
     continent
    -0.44
    idyl
    -0.43
     rege
    -0.43
    IO
    -0.42
     ModelExpression
    -0.42
    POSITIVE LOGITS
    contentLoaded
    0.69
    omiast
    0.69
    StoryboardSegue
    0.69
    Lähteet
    0.69
    afficheront
    0.66
     America
    0.64
    siębior
    0.64
    Rüyada
    0.64
    ❋
    0.63
     america
    0.62
    Activations Density 0.160%

    No Known Activations