© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15788
    Prev
    Next
    INDEX
    Explanations

    specific expressions or abbreviations related to scientific or medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WB
    -0.35
     toiminta
    -0.35
     totul
    -0.34
     Westen
    -0.34
     Whitfield
    -0.34
     Wirtschafts
    -0.34
     понятно
    -0.33
    țional
    -0.33
    文
    -0.33
    in
    -0.33
    POSITIVE LOGITS
     Sa
    1.84
    Sa
    1.73
     sa
    1.71
     SA
    1.61
    sa
    1.52
    SA
    1.45
     Sadie
    1.41
     Sá
    1.35
     Sap
    1.28
    Sap
    1.22
    Activations Density 0.185%

    No Known Activations