© 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. 7396
    Prev
    Next
    INDEX
    Explanations

    references to reports and statements made by sources, particularly in news contexts

    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
     sellado
    -0.55
     escova
    -0.52
     plegable
    -0.51
     Comprometido
    -0.51
     bambú
    -0.50
     vegetación
    -0.49
     plantel
    -0.49
    queryInterface
    -0.49
     terciopelo
    -0.49
     coordinación
    -0.48
    POSITIVE LOGITS
     CNN
    1.28
     Reuters
    1.18
     Newsweek
    1.12
     CNBC
    1.12
     BBC
    1.10
     Huffington
    1.05
    CNN
    1.05
     Bloomberg
    1.05
     Daily
    1.02
     NPR
    1.02
    Activations Density 0.751%

    No Known Activations