Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 4757
    Prev
    Next
    INDEX
    Explanations

    statements about economic viability and operational effectiveness related to businesses and organizations

    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
     strangest
    -0.50
    tocin
    -0.49
    MemoryWarning
    -0.48
     EconPapers
    -0.46
    Strange
    -0.45
    OLIS
    -0.45
     tab
    -0.45
    habitude
    -0.45
     Tab
    -0.45
    š
    -0.44
    POSITIVE LOGITS
     competitiveness
    1.05
     competitive
    1.04
     competi
    0.97
     competitivo
    0.96
     compete
    0.95
    competi
    0.95
     relevan
    0.93
    competitive
    0.93
     compéti
    0.88
     relevance
    0.87
    Activations Density 0.264%

    No Known Activations