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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 70641
    Prev
    Next
    INDEX
    Explanations

    references to cookies in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     Photocase
    -0.61
     Lordships
    -0.50
    FXML
    -0.49
    setVerticalGroup
    -0.49
     CreateTagHelper
    -0.48
    RTLU
    -0.46
     internetowa
    -0.46
     WebDriverWait
    -0.45
    xase
    -0.44
     للاسماء
    -0.44
    POSITIVE LOGITS
     Storage
    0.47
     storage
    0.45
    localStorage
    0.43
     localStorage
    0.42
     penyimpanan
    0.41
    SceneManagement
    0.40
     STORAGE
    0.40
    Parcelize
    0.39
    Storage
    0.38
     Players
    0.36
    Activations Density 0.003%

    No Known Activations