© 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. 30445
    Prev
    Next
    INDEX
    Explanations

    interrogative phrases, particularly focusing on "how," "what," and "why" questions

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

    how and why questions

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

    This neuron detects question openings—interrogative words and auxiliaries (e.g., "how", "do", "why", "when") that begin questions.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    rungsseite
    -0.39
     húmedo
    -0.37
     estekak
    -0.36
     deadliest
    -0.36
     vazio
    -0.36
     ciudadana
    -0.35
     spise
    -0.35
     raisonnable
    -0.35
     sisält
    -0.35
     purpoſe
    -0.35
    POSITIVE LOGITS
    How
    0.98
    how
    0.93
     how
    0.93
     How
    0.90
    howto
    0.85
    HOW
    0.81
     HOW
    0.80
     ways
    0.77
    Cómo
    0.76
     cómo
    0.75
    Activations Density 0.251%

    No Known Activations