© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 2951
    Prev
    Next
    INDEX
    Explanations

    sections that summarize or conclude information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sections that summarize or conclude content 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 @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hoor
    -0.53
    <!--
    -0.51
    łaś
    -0.51
    culously
    -0.51
    enza
    -0.51
     Cæsar
    -0.51
     Bevan
    -0.50
    zes
    -0.50
    toFloat
    -0.49
    tua
    -0.49
    POSITIVE LOGITS
     autorytatywna
    0.93
     Conclusion
    0.90
    setVerticalGroup
    0.87
    ậy
    0.86
    Conclusion
    0.86
     MainAxisSize
    0.85
     conclusion
    0.82
    Kesimpulan
    0.80
    สร
    0.79
    Conclusions
    0.79
    Activations Density 0.316%

    No Known Activations