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. 91218
    Prev
    Next
    INDEX
    Explanations

    terms related to mass production and high efficiency in manufacturing processes

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

    large quantities and speed

    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
    TagMode
    -0.57
     PopupWindow
    -0.48
     المعيارى
    -0.48
     فريبيس
    -0.47
    BagConstraints
    -0.45
    PreferredItem
    -0.43
    CppCodeGen
    -0.43
    UnusedPrivate
    -0.43
    PerformLayout
    -0.43
     Guen
    -0.43
    POSITIVE LOGITS
     resourceCulture
    0.36
     großem
    0.35
     schnelle
    0.35
     Autorisations
    0.35
     stora
    0.34
     швидко
    0.34
     быстро
    0.33
     große
    0.33
     hinweg
    0.33
    Speedy
    0.33
    Activations Density 0.070%

    No Known Activations