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. 2767
    Prev
    Next
    INDEX
    Explanations

    mechanical components and their interactions within machines

    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
    ratto
    -0.64
     antennae
    -0.58
     noDo
    -0.57
     تضيفلها
    -0.55
    antenna
    -0.54
     Stanis
    -0.54
    tserrat
    -0.53
    AnchorStyles
    -0.53
    Antenna
    -0.53
    leston
    -0.52
    POSITIVE LOGITS
     bearings
    0.97
     bearing
    0.83
     Bearings
    0.80
     Bearing
    0.80
     gears
    0.73
    Bearing
    0.71
     gear
    0.68
     teeth
    0.67
    Gear
    0.66
    gears
    0.66
    Activations Density 0.482%

    No Known Activations