Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 47112
    Prev
    Next
    INDEX
    Explanations

    keywords related to contracts and funding in a government or organizational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     vergüenza
    -0.33
    
    -0.32
     ladrillo
    -0.28
     הני
    -0.28
     précé
    -0.28
     يتيمه
    -0.27
     vocación
    -0.27
     vyš
    -0.27
    ane
    -0.27
    ViewImports
    -0.26
    POSITIVE LOGITS
     Contract
    0.78
     contract
    0.76
    Contract
    0.70
     Contracts
    0.68
    contract
    0.68
    BagConstraints
    0.65
     contracts
    0.65
     subcontra
    0.65
     contracting
    0.64
     contratto
    0.62
    Activations Density 0.036%

    No Known Activations