© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8833
    Prev
    Next
    INDEX
    Explanations

    terms related to biological or medical processes involving "end" or "endoscopic" contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.96
    sizeCache
    -0.88
    InteropServices
    -0.83
     Signalez
    -0.79
     препратки
    -0.78
     CURIAM
    -0.75
     StatefulWidget
    -0.75
    Revenir
    -0.70
    Gemeinden
    -0.69
    tvguidetime
    -0.69
    POSITIVE LOGITS
     end
    3.78
     End
    3.71
     END
    3.60
    End
    3.34
    END
    3.25
     ends
    2.97
     Ends
    2.71
    end
    2.69
     ending
    2.68
    ends
    2.52
    Activations Density 0.112%

    No Known Activations