© 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. 41-GEMMASCOPE-RES-16K
    11. 7446
    Prev
    Next
    INDEX
    Explanations

    references to academic writing structure and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.47
    MessageOf
    -0.45
     utafitiHapana
    -0.44
    úgó
    -0.41
    WireFormatLite
    -0.39
    eleste
    -0.37
    TokenNameLBRACE
    -0.36
     &___
    -0.36
     disambiguazione
    -0.35
    actéristique
    -0.35
    POSITIVE LOGITS
     concluding
    2.23
     finish
    2.22
     ending
    2.22
     conclude
    2.19
     finishing
    2.19
     concludes
    2.14
     conclusion
    2.14
     finishes
    2.08
     concluded
    2.02
    finish
    1.88
    Activations Density 1.146%

    No Known Activations