© 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. 3-GEMMASCOPE-RES-16K
    11. 9298
    Prev
    Next
    INDEX
    Explanations

    the opening token of various sections in text or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagHelpers
    -0.81
    gehend
    -0.63
    RegressionTest
    -0.62
    MemoryWarning
    -0.61
     ujednoznacz
    -0.60
     Grüsse
    -0.55
     inhoud
    -0.55
     ExecuteAsync
    -0.54
    Халык
    -0.52
     PhpStorm
    -0.52
    POSITIVE LOGITS
     Guang
    0.43
     chine
    0.42
     consul
    0.42
     stock
    0.42
     ment
    0.41
     yin
    0.41
    Capit
    0.41
     auge
    0.40
     daim
    0.40
    bolista
    0.40
    Activations Density 0.042%

    No Known Activations