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. 4741
    Prev
    Next
    INDEX
    Explanations

    historical figures involved in political controversies and their impacts

    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
    دانشنامهٔ
    -0.77
     ২০১
    -0.71
     acrylique
    -0.69
     Wikiseite
    -0.69
     actuellement
    -0.66
     currently
    -0.66
     derzeit
    -0.66
     actuels
    -0.62
     المعيارى
    -0.61
     aktuell
    -0.60
    POSITIVE LOGITS
    =“
    0.61
     reformers
    0.55
     telegram
    0.54
     tuber
    0.53
     newspapers
    0.53
    presto
    0.52
    <bos>
    0.52
     soon
    0.51
    WithIOException
    0.51
     scandal
    0.50
    Activations Density 1.512%

    No Known Activations