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. 0-GEMMASCOPE-RES-16K
    6. 9872
    Prev
    Next
    INDEX
    Explanations

    statements reflecting personal feelings and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ponses
    -0.85
    发表于
    -0.81
    %?
    -0.77
     referrerpolicy
    -0.76
    endregion
    -0.74
    脚注の使い方
    -0.68
    +#+#
    -0.68
    Actually
    -0.66
    Definitely
    -0.66
     really
    -0.65
    POSITIVE LOGITS
     nahilalakip
    0.62
     vecka
    0.54
     autobuses
    0.54
     składa
    0.51
     kumpulan
    0.50
     esetben
    0.49
     brukt
    0.49
     composizione
    0.49
     borsa
    0.49
     planches
    0.48
    Activations Density 1.106%

    No Known Activations