Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-GEMMASCOPE-RES-16K
    6. 10198
    Prev
    Next
    INDEX
    Explanations

    references to operating systems and software, particularly Microsoft products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.85
    :✨
    -0.85
    ConstraintMaker
    -0.81
     فريبيس
    -0.81
    MigrationBuilder
    -0.78
    SequentialGroup
    -0.77
     Waray
    -0.77
    IntoConstraints
    -0.76
     utafitiHapana
    -0.75
    oredCriteria
    -0.73
    POSITIVE LOGITS
     Windows
    0.69
     Outlook
    0.69
     windows
    0.64
     Microsoft
    0.60
    Windows
    0.58
     Word
    0.56
    Microsoft
    0.55
     XP
    0.54
    windows
    0.52
     SharePoint
    0.50
    Activations Density 0.565%

    No Known Activations