© 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. 1516
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate reporting or referencing information from specific sources

    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
     plegable
    -0.56
     sellado
    -0.50
     productivo
    -0.49
     imprimible
    -0.49
    inSlope
    -0.48
     terciopelo
    -0.48
     stratégique
    -0.48
     táctil
    -0.48
     ejército
    -0.48
     eléctrico
    -0.47
    POSITIVE LOGITS
     CNN
    1.45
     Reuters
    1.37
     CNBC
    1.33
     BBC
    1.30
     Newsweek
    1.28
     Daily
    1.27
     NPR
    1.23
     Huffington
    1.23
    CNN
    1.21
     Times
    1.19
    Activations Density 1.296%

    No Known Activations