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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 12868
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sometimes" and variations indicating frequency or occurrence

    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
     purpoſe
    -0.70
     californ
    -0.70
    脚注の使い方
    -0.70
     zdroj
    -0.69
     위한
    -0.68
    Hentet
    -0.66
     ſet
    -0.66
     perſon
    -0.66
     készült
    -0.63
     læng
    -0.62
    POSITIVE LOGITS
     sometimes
    2.24
    sometimes
    2.07
     Sometimes
    2.05
    Sometimes
    2.04
     occasionally
    1.65
     parfois
    1.65
     often
    1.63
     manchmal
    1.62
     oftentimes
    1.57
     иногда
    1.51
    Activations Density 0.115%

    No Known Activations