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. 2460
    Prev
    Next
    INDEX
    Explanations

    references to formal structures and systems

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

    Follows punctuation

    np_acts-logits-general · gemini-2.0-flash

    . followed by Q, Attached, package, Arsenic

    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
    :+:
    -0.82
    Portály
    -0.74
    obut
    -0.65
    terness
    -0.65
    '],$
    -0.63
    '])){
    
    -0.63
    devamını
    -0.62
    "]();
    -0.62
     Sider
    -0.62
    ']):
    -0.60
    POSITIVE LOGITS
    rrggbb
    0.64
     Baillargeon
    0.59
     specialties
    0.57
     honte
    0.56
     unrivalled
    0.55
     unsurpassed
    0.54
     сможете
    0.54
    Genuine
    0.53
     Genuine
    0.53
     completa
    0.52
    Activations Density 0.048%

    No Known Activations