© 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. 3-GEMMASCOPE-RES-16K
    11. 2488
    Prev
    Next
    INDEX
    Explanations

    terms related to document endings or conclusions

    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
     ModelExpression
    -1.07
    twimg
    -1.00
     تعدى
    -1.00
     CURIAM
    -0.98
    JspWriter
    -0.94
    PreferredItem
    -0.92
     MainAxisSize
    -0.87
     ?>>
    -0.86
    RunAsync
    -0.85
    WriteBarrier
    -0.85
    POSITIVE LOGITS
     End
    2.35
    End
    2.15
     END
    1.55
     Endo
    1.17
    END
    1.10
    setEnd
    0.92
     endos
    0.89
     ende
    0.89
    getEnd
    0.83
     endo
    0.78
    Activations Density 0.093%

    No Known Activations