© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 126311
    Prev
    Next
    INDEX
    Explanations

    predicative statements related to authority and judgment in a legal context

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

    real-time business decisions

    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
     للمعارف
    -0.40
     يتيمه
    -0.36
    aktifkan
    -0.34
    setdefault
    -0.33
    ariConfig
    -0.33
     phare
    -0.31
     Hitam
    -0.31
     Chwiliwch
    -0.31
    Erstellt
    -0.29
     enfans
    -0.29
    POSITIVE LOGITS
    :✨
    0.75
    findpost
    0.55
     Мексичка
    0.54
    oredCriteria
    0.52
     also
    0.51
    tagHelperRunner
    0.50
     propOrder
    0.49
    GeneratedValue
    0.48
    WriteLiteral
    0.48
     AppDelegate
    0.48
    Activations Density 0.003%

    No Known Activations