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. 2166
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistics, reports, and economic analysis

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

    Mentions statistics or statistical offices

    np_acts-logits-general · gemini-2.0-flash

    statistic and study

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     propOrder
    -0.83
    Begriffsklä
    -0.74
    sidemargin
    -0.72
     &___
    -0.72
    WithIOException
    -0.67
     viewDidLoad
    -0.62
     setDescription
    -0.62
     transfieras
    -0.60
    hasMoreElements
    -0.59
     betweenstory
    -0.59
    POSITIVE LOGITS
     statistics
    2.55
     stats
    2.16
     Statistics
    2.10
     statistic
    2.04
    statistics
    2.01
    Statistics
    1.94
     statistik
    1.93
     statistical
    1.88
     STATISTICS
    1.77
     Statistic
    1.77
    Activations Density 0.493%

    No Known Activations