© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 10236
    Prev
    Next
    INDEX
    Explanations

    mentions of the "Br" term related to a specific subject or context in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Terme
    -0.60
     afric
    -0.58
    setVerticalGroup
    -0.57
     Lottie
    -0.57
    soka
    -0.53
     Overton
    -0.53
    MTS
    -0.52
     Tobi
    -0.52
     fête
    -0.52
    kaido
    -0.52
    POSITIVE LOGITS
     Br
    2.81
     br
    2.70
    br
    2.70
    bra
    2.69
     BR
    2.67
    Br
    2.67
     Bra
    2.59
    Bra
    2.58
    BR
    2.50
     bra
    2.45
    Activations Density 0.028%

    No Known Activations