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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114869
    Prev
    Next
    INDEX
    Explanations

    instances of the "GET" HTTP method

    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
     deleteById
    -0.73
     columnIndex
    -0.73
     newNode
    -0.70
     companyId
    -0.70
     accountId
    -0.69
     onClose
    -0.68
     columnName
    -0.67
     itemId
    -0.65
     fullName
    -0.65
     errorMsg
    -0.65
    POSITIVE LOGITS
    Get
    1.06
    get
    1.03
    GET
    0.97
     Get
    0.96
     GET
    0.91
     get
    0.89
    Getter
    0.71
     Obtén
    0.70
    Gets
    0.68
     Geta
    0.67
    Activations Density 0.020%

    No Known Activations