© 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. 3-GEMMASCOPE-RES-16K
    11. 5857
    Prev
    Next
    INDEX
    Explanations

    sections and words that indicate summarization or conclusion in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bulge
    -0.52
     becauſe
    -0.47
    とある
    -0.46
    éal
    -0.46
    zumaki
    -0.46
    daq
    -0.45
    astrous
    -0.45
    ์ตูน
    -0.45
    crumb
    -0.44
    ığınız
    -0.44
    POSITIVE LOGITS
     Conclusions
    1.15
     Conclusion
    1.13
     CONCLUSION
    1.13
    Conclusions
    1.07
    Conclusion
    1.06
    CONCLUSIONS
    1.03
     CONCLUSIONS
    1.02
    CONCLUSION
    0.97
     conclusion
    0.96
    Fazit
    0.96
    Activations Density 0.356%

    No Known Activations