© 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. 40-GEMMASCOPE-RES-16K
    11. 6292
    Prev
    Next
    INDEX
    Explanations

    sections and phrases related to conclusions and summaries in academic papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     erstmal
    -0.40
    出版年
    -0.39
     وتسجيلات
    -0.38
    úgó
    -0.38
    ulement
    -0.37
     Signalez
    -0.37
     Exactos
    -0.37
    PreferredItem
    -0.36
    rifugal
    -0.36
    unächst
    -0.35
    POSITIVE LOGITS
     conclusion
    2.81
     concluding
    2.73
     conclude
    2.56
     concludes
    2.47
    conclusion
    2.45
    Conclusion
    2.42
     Conclusion
    2.41
     Concluding
    2.34
     concluded
    2.28
    Concluding
    2.28
    Activations Density 0.884%

    No Known Activations