© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15085
    Prev
    Next
    INDEX
    Explanations

    transitional phrases indicating a conclusion or summary

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

    Sentences starting with "Finally" or "Lastly"

    np_acts-logits-general · gemini-2.0-flash

    finally, lastly, concluding remarks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cité
    -0.41
     immediately
    -0.39
     concurrently
    -0.36
    تقاوى
    -0.35
     Mérida
    -0.34
     liền
    -0.33
     склад
    -0.33
     Comunidad
    -0.32
    是有
    -0.32
    Immediately
    -0.32
    POSITIVE LOGITS
    principalTable
    0.80
     lastly
    0.74
     Lastly
    0.72
    Datuak
    0.68
     infine
    0.68
    Lastly
    0.68
     Finally
    0.67
    
    0.67
    featureID
    0.66
    最後は
    0.66
    Activations Density 0.395%

    No Known Activations