© 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. 294
    Prev
    Next
    INDEX
    Explanations

    specific code structure elements, particularly slashes and the beginning of sections

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

    occurrences of the slash character

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

    nor prejudiced, combined forces, York City

    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
     BorderRadius
    -0.74
    ViewFeatures
    -0.72
    IntoConstraints
    -0.66
    Jîn
    -0.62
    TargetException
    -0.61
     bahay
    -0.61
    <?
    -0.60
    XmlAttribute
    -0.60
    ftagPool
    -0.57
    antMatchers
    -0.57
    POSITIVE LOGITS
     الحره
    0.54
    eschön
    0.45
     softly
    0.44
    ---*/
    0.44
     local
    0.43
    ponge
    0.43
     rightfully
    0.43
     of
    0.42
    TEntity
    0.41
    endsection
    0.40
    Activations Density 0.010%

    No Known Activations