© 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. 65
    Prev
    Next
    INDEX
    Explanations

    beginning markers or indicators of new sections or topics in text

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

    the presence of structured markup or annotations in text

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

    company names and prices

    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
    mentaires
    -0.50
    ​=
    -0.47
     Islas
    -0.46
    necedor
    -0.44
    TCA
    -0.43
    Linker
    -0.43
    daille
    -0.41
    koliv
    -0.41
    idge
    -0.40
    ritch
    -0.40
    POSITIVE LOGITS
    principalColumn
    0.93
    expandindo
    0.91
     Paglinawan
    0.77
     "..\..\..\
    0.73
    WithIOException
    0.73
    UIControlState
    0.69
    featureID
    0.66
     թվական
    0.66
    حياتها
    0.66
    onViewCreated
    0.66
    Activations Density 0.011%

    No Known Activations