© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 100135
    Prev
    Next
    INDEX
    Explanations

    the word "nicely" or variations suggesting favorable or pleasing conditions

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

    adverbs describing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vær
    -0.45
     jangka
    -0.42
     desierto
    -0.39
     monasterio
    -0.39
     télévis
    -0.38
     těž
    -0.38
     Komunikasi
    -0.36
     cardiaque
    -0.36
     rare
    -0.36
     flyg
    -0.36
    POSITIVE LOGITS
     nicely
    1.66
    Nicely
    1.35
     neatly
    1.02
     smartly
    0.86
    pely
    0.84
     decently
    0.74
     Properly
    0.74
     sweetly
    0.73
    properly
    0.69
     politely
    0.68
    Activations Density 0.002%

    No Known Activations