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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 38748
    Prev
    Next
    INDEX
    Explanations

    references to buyers in a real estate 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
    specialchars
    -0.57
    fohl
    -0.54
     Roc
    -0.53
     Rhodes
    -0.52
     Rojas
    -0.50
    fxml
    -0.49
     "..\..\..\
    -0.49
    printStackTrace
    -0.49
     Kof
    -0.48
     Moss
    -0.48
    POSITIVE LOGITS
    Buyer
    1.30
     Buyer
    1.25
     buyer
    1.23
    buyer
    1.23
     Buyers
    1.09
     Käufer
    1.09
    Buyers
    1.08
     buyers
    1.05
     acheteurs
    1.01
    buyers
    1.00
    Activations Density 0.004%

    No Known Activations