© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 27664
    Prev
    Next
    INDEX
    Explanations

    calls to action for physical activities and community involvement

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

    exercise for, art out of

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects imperative commands or activity prompts — short instructions urging the reader to do an action or participate in an activity.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    verifyException
    -0.55
    AndEndTag
    -0.53
    كويكب
    -0.45
    mappedBy
    -0.44
     ujednoznacz
    -0.43
     Reverso
    -0.41
    marque
    -0.41
    
    -0.40
    urlpatterns
    -0.40
     requestCode
    -0.40
    POSITIVE LOGITS
    GEBURTS
    0.40
    énario
    0.39
     Bunk
    0.35
     yourself
    0.35
    nerstag
    0.35
    onday
    0.35
    ➟
    0.35
    Portály
    0.34
    ilber
    0.34
    [::-
    0.33
    Activations Density 0.023%

    No Known Activations