© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122766
    Prev
    Next
    INDEX
    Explanations

    legal and diplomatic terms related to international relations and agreements

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

    diplomatic and governmental agreements

    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
    aarrggbb
    -0.70
    MessageTagHelper
    -0.66
     مرئيه
    -0.60
    RenderAtEndOf
    -0.60
    WithIOException
    -0.60
    oredCriteria
    -0.59
    Personendaten
    -0.59
    parsedMessage
    -0.58
    IsMutable
    -0.58
    adaptiveStyles
    -0.57
    POSITIVE LOGITS
     bilateral
    0.45
     diplomatic
    0.40
     counterpart
    0.37
     Bilateral
    0.36
    Bil
    0.36
    Diplom
    0.35
     Diplomatic
    0.34
    grà
    0.34
    USAL
    0.34
     officials
    0.33
    Activations Density 0.058%

    No Known Activations