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. 1836
    Prev
    Next
    INDEX
    Explanations

    phrases related to health studies and their findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following "in" or "of"

    np_acts-logits-general · gemini-2.0-flash

    in recent times

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    enumi
    -0.78
    +#+#
    -0.75
    पया
    -0.70
     wherever
    -0.69
    ViewFeatures
    -0.67
     Wherever
    -0.66
    JsonFormat
    -0.66
     whatever
    -0.66
    Everyone
    -0.66
    anything
    -0.65
    POSITIVE LOGITS
     two
    0.79
     randomly
    0.77
     three
    0.73
     selected
    0.70
     four
    0.69
     recently
    0.68
     commercially
    0.67
     commercial
    0.63
     five
    0.62
     newly
    0.62
    Activations Density 2.001%

    No Known Activations