© 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. 9-GEMMASCOPE-RES-16K
    11. 7690
    Prev
    Next
    INDEX
    Explanations

    expressions related to conclusions and inferences in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nestjs
    -0.68
    didSet
    -0.66
    andu
    -0.66
    spli
    -0.63
    pherd
    -0.62
    bitField
    -0.62
    Trev
    -0.61
     berlaku
    -0.61
     Ever
    -0.61
    Véxase
    -0.60
    POSITIVE LOGITS
     conclusions
    1.54
     conclusion
    1.45
     conclude
    1.31
     Conclusions
    1.28
    conclusion
    1.22
     concludes
    1.16
    impulan
    1.14
     Conclusion
    1.08
     concluded
    1.06
     conclusión
    1.04
    Activations Density 0.151%

    No Known Activations