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. 20-GEMMASCOPE-RES-16K
    6. 2008
    Prev
    Next
    INDEX
    Explanations

    dates and related temporal expressions

    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
     ontem
    -0.77
     tonight
    -0.75
     tomorrow
    -0.74
    parsedMessage
    -0.73
     ngayon
    -0.73
     heutigen
    -0.72
     demain
    -0.71
     hoje
    -0.71
     momentan
    -0.69
     today
    -0.67
    POSITIVE LOGITS
     after
    0.70
     when
    0.62
    的一天
    0.62
    after
    0.60
     tepat
    0.59
     came
    0.58
     we
    0.58
     після
    0.57
     during
    0.57
     he
    0.57
    Activations Density 0.347%

    No Known Activations