© 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. 19-GEMMASCOPE-RES-16K
    11. 3545
    Prev
    Next
    INDEX
    Explanations

    instances of the root "Bur" or its variations, suggesting a focus on words related to "Borough" or "Burley."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.68
    TemporalType
    -0.68
    reportWebVitals
    -0.66
    abetes
    -0.63
    Xaml
    -0.62
    IntoConstraints
    -0.61
    EndGlobalSection
    -0.61
    Tikang
    -0.60
    ValueStyle
    -0.59
     Савезне
    -0.59
    POSITIVE LOGITS
     Bor
    0.88
    bor
    0.84
     bor
    0.82
    Bor
    0.77
    BOR
    0.75
     BOR
    0.67
     bur
    0.64
     Бор
    0.60
     Burrows
    0.60
    boru
    0.60
    Activations Density 0.065%

    No Known Activations