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. 2249
    Prev
    Next
    INDEX
    Explanations

    mentions of open-source licenses and related information

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

    open source licenses

    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
    ModelAdmin
    -0.54
    tanleria
    -0.53
    serviceWorker
    -0.52
    quelize
    -0.48
    はじめに
    -0.46
    modb
    -0.45
    rawDesc
    -0.45
     vayas
    -0.44
    PageModule
    -0.43
     vœ
    -0.43
    POSITIVE LOGITS
    opensource
    2.77
     open
    0.68
    开源
    0.67
    open
    0.65
     OSS
    0.63
     Open
    0.61
     OPEN
    0.59
    Open
    0.58
     Opens
    0.55
     isOpen
    0.55
    Activations Density 0.001%

    No Known Activations