© 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. 39-GEMMASCOPE-RES-16K
    11. 1615
    Prev
    Next
    INDEX
    Explanations

    instances of the prefix "Tra" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.66
    GEBURTSDATUM
    -0.63
     ModelRenderer
    -0.54
     مشين
    -0.53
    addPreferredGap
    -0.52
    isContained
    -0.51
    WireFormatLite
    -0.50
     AssemblyVersion
    -0.50
    ########.
    -0.50
    FieldBuilder
    -0.49
    POSITIVE LOGITS
     tra
    0.43
    URLException
    0.40
     тра
    0.38
     Тра
    0.36
     Tra
    0.35
    tra
    0.30
     tramo
    0.30
    umat
    0.30
    Tra
    0.30
     Cielo
    0.29
    Activations Density 0.211%

    No Known Activations