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. 17-GEMMASCOPE-RES-65K
    6. 28526
    Prev
    Next
    INDEX
    Explanations

    terms related to waste management and environmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.59
     متعلقه
    -0.58
    cipar
    -0.57
    >*/
    -0.55
    authentic
    -0.55
    webElementGuid
    -0.54
     Mortgage
    -0.53
    PerformLayout
    -0.52
    Mortgage
    -0.50
    XmlAccessType
    -0.50
    POSITIVE LOGITS
     landfill
    1.09
     disposal
    1.09
     Disposal
    0.99
     Waste
    0.94
     waste
    0.94
    Disposal
    0.92
     landfills
    0.91
     Landfill
    0.89
    waste
    0.85
     WASTE
    0.85
    Activations Density 0.068%

    No Known Activations