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. 10374
    Prev
    Next
    INDEX
    Explanations

    concepts related to healthcare research methodologies

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

    Followed by research/study related words

    np_acts-logits-general · gemini-2.0-flash

    research and its results

    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
    Portail
    -0.61
    cibly
    -0.60
    躇
    -0.60
    athies
    -0.59
    hpur
    -0.57
    ariki
    -0.56
    UKAN
    -0.55
     nominally
    -0.54
     energetically
    -0.54
    綜合報導
    -0.53
    POSITIVE LOGITS
     research
    0.72
     researcher
    0.72
    IBOutlet
    0.68
     investigación
    0.67
     researches
    0.63
    research
    0.63
    Research
    0.63
     researched
    0.63
     penelitian
    0.60
     Research
    0.59
    Activations Density 0.174%

    No Known Activations