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. 8679
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical data related to sports and performance metrics

    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
    ipedi
    -0.47
    khu
    -0.43
     Hus
    -0.40
    otomy
    -0.40
    metic
    -0.40
    PostBack
    -0.39
    glieder
    -0.39
    flavored
    -0.38
     елның
    -0.38
     flank
    -0.38
    POSITIVE LOGITS
     offered
    1.05
     received
    1.04
     eaten
    1.01
     consumed
    0.99
     taken
    0.98
     traded
    0.97
     undertaken
    0.96
     sold
    0.95
     consulted
    0.94
     encountered
    0.94
    Activations Density 0.948%

    No Known Activations