© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 2708
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Bre" and its variations, possibly indicating references to a person or character involved in significant actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setTotal
    -0.41
     qua
    -0.35
    ETRIC
    -0.33
    argento
    -0.33
     onBind
    -0.33
     Hein
    -0.33
    Total
    -0.33
     Hague
    -0.32
     estimés
    -0.32
     Total
    -0.31
    POSITIVE LOGITS
     Administrativna
    0.77
    Bre
    0.75
     Bre
    0.73
    rungsseite
    0.69
     Wikimedijinoj
    0.67
     bre
    0.63
     BRE
    0.61
     faſt
    0.60
    reportWebVitals
    0.58
    Break
    0.57
    Activations Density 0.139%

    No Known Activations