© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 3255
    Prev
    Next
    INDEX
    Explanations

    statements that indicate conclusions or outcomes drawn from discussions and research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     userManager
    -0.67
    Véxase
    -0.66
    didSet
    -0.65
     Ever
    -0.64
    bitField
    -0.63
    iecie
    -0.63
     SP
    -0.62
    writeByte
    -0.62
    spli
    -0.62
    ervo
    -0.61
    POSITIVE LOGITS
     conclusions
    1.53
     conclusion
    1.46
     Conclusions
    1.28
     conclude
    1.26
    conclusion
    1.24
    impulan
    1.22
     concludes
    1.15
     Conclusion
    1.10
     conclu
    1.07
    结论
    1.06
    Activations Density 0.143%

    No Known Activations