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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8224
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest doubt, disagreement, or questioning of established truths

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

    excessive movement or opposition

    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-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
    ❔
    -0.31
     wissen
    -0.30
     Menor
    -0.29
     Mission
    -0.29
     maît
    -0.28
     Major
    -0.28
    bukti
    -0.28
     brand
    -0.28
    トル
    -0.27
     courses
    -0.27
    POSITIVE LOGITS
     surla
    0.83
     Wikimedijinoj
    0.77
    Personendaten
    0.74
    ьаж
    0.69
    UnusedPrivate
    0.69
    AntiForgeryToken
    0.66
    Diweddarwch
    0.66
    Bibliograf
    0.65
     autorytatywna
    0.64
     }{@
    0.64
    Activations Density 0.282%

    No Known Activations