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. 1939
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols related to algebra and geometry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    subequations
    -0.51
    Eq
    -0.50
     scenarios
    -0.47
     Eq
    -0.46
     Mathematical
    -0.46
     mathematical
    -0.44
    anema
    -0.43
    Գ
    -0.43
     Equation
    -0.43
    Math
    -0.42
    POSITIVE LOGITS
    ConstraintMaker
    1.01
     gyhoeddwyd
    0.96
     kaarangay
    0.85
    ViewFeatures
    0.85
     AssemblyCulture
    0.84
     disambiguazione
    0.82
    
    0.79
    DockStyle
    0.77
     समीक्षाओं
    0.77
    anyahu
    0.75
    Activations Density 4.660%

    No Known Activations