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. 25-GEMMASCOPE-RES-16K
    6. 1851
    Prev
    Next
    INDEX
    Explanations

    key economic indicators and projections related to market growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.76
     linkovi
    -0.76
     المعيارى
    -0.69
     فريبيس
    -0.65
    EndInit
    -0.63
    hdys
    -0.62
    Collegamenti
    -0.61
     AssemblyTitle
    -0.61
    awtextra
    -0.60
     Walkover
    -0.60
    POSITIVE LOGITS
     growth
    1.31
    growth
    1.01
     Growth
    0.93
    Growth
    0.91
     GROWTH
    0.89
     rapid
    0.88
     fastest
    0.87
     exponential
    0.85
     explosive
    0.85
     croissance
    0.85
    Activations Density 0.285%

    No Known Activations