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 - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 8130
    Prev
    Next
    INDEX
    Explanations

    references to business relationships and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     soltanto
    -0.80
     cotone
    -0.76
     perciò
    -0.72
     marrone
    -0.71
     convenable
    -0.62
     vestiti
    -0.59
     cappuccio
    -0.59
     riguardo
    -0.59
     vanske
    -0.59
     sostanze
    -0.59
    POSITIVE LOGITS
     leveraging
    1.07
    NameInMap
    0.94
    DockStyle
    0.90
     leveraged
    0.87
     proactively
    0.80
     learnings
    0.79
     leverage
    0.79
    ArrowToggle
    0.78
     Leverage
    0.78
     incentiv
    0.78
    Activations Density 0.390%

    No Known Activations