© 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. 9-GEMMASCOPE-RES-16K
    11. 8605
    Prev
    Next
    INDEX
    Explanations

    references to comprehensive collections or aggregations of data and information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.63
    Билгалдахарш
    -0.44
     parfois
    -0.42
     mancher
    -0.39
     qualcosa
    -0.39
     sometimes
    -0.38
    Хьажоргаш
    -0.38
     Arque
    -0.37
    少々
    -0.37
    Sometimes
    -0.36
    POSITIVE LOGITS
     모든
    0.82
     wszystkie
    0.81
     everything
    0.80
    すべての
    0.80
     Semua
    0.79
     todas
    0.78
    全ての
    0.78
     تمامی
    0.75
     सभी
    0.75
     Todas
    0.73
    Activations Density 0.963%

    No Known Activations