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-2-2B
    4. Residual Stream - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 43206
    Prev
    Next
    INDEX
    Explanations

    mentions of "application" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WaitForSeconds
    -0.85
    التالي
    -0.78
    elemField
    -0.75
    NewGuid
    -0.73
     juridiques
    -0.73
    makeText
    -0.72
    sendRedirect
    -0.72
     miR
    -0.71
    ofollow
    -0.71
     CURLOPT
    -0.70
    POSITIVE LOGITS
     application
    1.48
    application
    1.31
     applications
    1.30
     Application
    1.27
    Application
    1.27
    getApplication
    1.26
     getApplication
    1.19
    APPLICATION
    1.13
    Applications
    1.11
     Applications
    1.10
    Activations Density 0.011%

    No Known Activations