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. 5-GEMMASCOPE-RES-16K
    6. 7463
    Prev
    Next
    INDEX
    Explanations

    phrases that express a sense of urgency or inevitability in various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     or
    -0.52
    (
    -0.48
     Сере
    -0.47
    me
    -0.46
      
    -0.45
    zin
    -0.44
     representing
    -0.44
    mit
    -0.43
    const
    -0.43
    [
    -0.43
    POSITIVE LOGITS
    Tudo
    1.16
     المعيارى
    1.09
     Tudo
    1.06
     tudo
    0.99
     transférez
    0.98
     betweenstory
    0.96
    ^(@)
    0.95
     kasarigan
    0.93
     Everything
    0.91
    abestanden
    0.90
    Activations Density 0.146%

    No Known Activations