© 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-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 13224
    Prev
    Next
    INDEX
    Explanations

    names and references to Danish places, landmarks, and historical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nød
    -0.66
     spørs
    -0.59
     الحره
    -0.59
    脚注の使い方
    -0.59
     måte
    -0.56
     læng
    -0.56
    ThroughAttribute
    -0.56
     nødven
    -0.56
    ագրություններ
    -0.54
     tjen
    -0.54
    POSITIVE LOGITS
     Danish
    1.30
     Denmark
    1.16
    Danish
    1.13
     Copenhagen
    1.13
     danish
    1.05
    Denmark
    1.02
     Dinamarca
    0.95
     Danemark
    0.91
     Aarhus
    0.90
     Danes
    0.88
    Activations Density 0.580%

    No Known Activations