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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 113823
    Prev
    Next
    INDEX
    Explanations

    terms related to immunology and feature selection in data classification

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

    definition/description followed by category

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     kasarigan
    -0.56
    GOTREF
    -0.55
     Biôgrafia
    -0.55
     layui
    -0.55
    Derbyniad
    -0.54
     AssemblyVersion
    -0.53
    səhifə
    -0.52
     kaynağından
    -0.52
    Spoljašnje
    -0.52
     سكانية
    -0.51
    POSITIVE LOGITS
     conversely
    0.36
     Photocase
    0.36
     sitten
    0.35
     ویکی‌پدیای
    0.33
     milder
    0.32
    則是
    0.32
     betweenstory
    0.32
     parezca
    0.32
    jednoc
    0.32
    исленность
    0.32
    Activations Density 0.020%

    No Known Activations