© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11445
    Prev
    Next
    INDEX
    Explanations

    keywords related to international agreements and collaborations

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

    international agreements or organizations

    np_acts-logits-general · gemini-2.0-flash

    United Nations and international treaties

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    MessageTagHelper
    -0.67
     BoxFit
    -0.54
     }{@
    -0.53
     nahilalakip
    -0.52
    $_['
    -0.48
     invokingState
    -0.48
     TVA
    -0.47
     SQLAlchemy
    -0.47
    पया
    -0.47
    LLC
    -0.46
    POSITIVE LOGITS
     multilateral
    0.60
     universality
    0.54
     wereld
    0.49
    各国
    0.48
     världen
    0.47
     mondial
    0.47
     gouvernements
    0.47
     international
    0.47
    humanité
    0.46
     goederen
    0.46
    Activations Density 0.186%

    No Known Activations