© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 5372
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts, particularly related to API structure and product categorization

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

    product identifiers and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.56
     Sheldon
    -0.51
     CEM
    -0.50
    Sheldon
    -0.48
    ListGroup
    -0.47
     BoxFit
    -0.47
     Wilton
    -0.47
     BMD
    -0.46
    Mailing
    -0.46
     TType
    -0.46
    POSITIVE LOGITS
    productId
    1.79
     productId
    1.66
    ProductId
    1.23
     ProductService
    1.09
    ProductService
    1.03
    ProductID
    0.98
    getProducts
    0.81
    ProductName
    0.81
    productName
    0.79
    getProduct
    0.77
    Activations Density 0.000%

    No Known Activations