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. 20-GEMMASCOPE-RES-16K
    6. 16026
    Prev
    Next
    INDEX
    Explanations

    references to economic concepts and issues related to healthcare systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    HomeAsUpEnabled
    -0.58
     @}
    -0.54
    FileDescriptor
    -0.53
    եռ
    -0.48
     RVA
    -0.47
    Tracce
    -0.47
     становника
    -0.46
     geli
    -0.45
    cahontas
    -0.45
    кина
    -0.44
    POSITIVE LOGITS
     incentives
    0.90
    Incenti
    0.80
     incentive
    0.80
    incenti
    0.74
     Prisoner
    0.71
     Incentives
    0.69
     Incentive
    0.64
     préférences
    0.62
     game
    0.62
     preferences
    0.62
    Activations Density 0.826%

    No Known Activations