© 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 EvalsExportsinterp-engineNEWAPI 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. 72941
    Prev
    Next
    INDEX
    Explanations

    moments of realization and emotional responses in narratives

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

    Japanese and foreign words with punctuation

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

    moments of sudden realization or shock — tokens signaling someone suddenly noticing, realizing, or exclaiming in surprise.

    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
     مرئيه
    -0.59
    intios
    -0.58
     Мексичка
    -0.57
     Downvote
    -0.53
     Budd
    -0.51
     cherchés
    -0.50
    RTLD
    -0.50
     linkovi
    -0.50
    ///</
    -0.49
    存于互联网档案馆
    -0.49
    POSITIVE LOGITS
    zęd
    0.28
    getDoctrine
    0.28
     realize
    0.27
     revisa
    0.27
    melidir
    0.26
    ksesta
    0.26
     داری
    0.26
    гут
    0.25
     stunned
    0.25
     discriminación
    0.25
    Activations Density 0.065%

    No Known Activations