Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9725
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations involving functions and their properties

    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
     mémoire
    -0.55
     énergé
    -0.51
     esprits
    -0.47
     automatiques
    -0.47
     Mémoires
    -0.44
    ênio
    -0.44
    mittel
    -0.44
    urlpatterns
    -0.43
     detik
    -0.43
    eclipse
    -0.43
    POSITIVE LOGITS
     lenker
    0.96
     EconPapers
    0.92
    postsleuth
    0.76
    aarrggbb
    0.73
     ostavi
    0.73
    లాలు
    0.71
    Personendaten
    0.70
    ImageContext
    0.68
    Tembelea
    0.66
    celotti
    0.66
    Activations Density 1.089%

    No Known Activations