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. 10208
    Prev
    Next
    INDEX
    Explanations

    references to diversity and inclusion

    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
    Geplaatst
    -0.92
    Diwedd
    -0.80
     geslacht
    -0.77
    AnchorStyles
    -0.74
    setVerticalGroup
    -0.74
    abestanden
    -0.73
    脚注の使い方
    -0.72
    ValueGenerated
    -0.70
    archiviato
    -0.70
     Winaray
    -0.69
    POSITIVE LOGITS
    SupportActionBar
    0.68
     المعيارى
    0.61
    ConstraintMaker
    0.61
    ۣ
    0.60
    GEBURTSDATUM
    0.58
    первых
    0.57
    Jîn
    0.57
    .")
    
    0.55
    SBATCH
    0.55
    medriver
    0.54
    Activations Density 1.684%

    No Known Activations