© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 180
    Prev
    Next
    INDEX
    Explanations

    references to tutoring services and academic support resources

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

    references to educational support and tutoring services

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

    quantifiers or specific continuations

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    Història
    -0.61
     guida
    -0.59
     történ
    -0.58
     verrez
    -0.56
     cortas
    -0.55
     tölt
    -0.55
     honom
    -0.53
     szinte
    -0.53
    ngOn
    -0.53
     pieles
    -0.52
    POSITIVE LOGITS
     Baillargeon
    0.85
    DoubleQuotes
    0.82
     كومونز
    0.77
    DataAnnotations
    0.70
    kloped
    0.70
    )";
    0.68
     CURIAM
    0.68
    GEBURTS
    0.67
     ujednoznacz
    0.66
    RenderAtEndOf
    0.65
    Activations Density 0.007%

    No Known Activations