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. 12424
    Prev
    Next
    INDEX
    Explanations

    language elements related to programming conditions and assignments

    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
     الحره
    -0.78
     iſt
    -0.74
    BibitemShut
    -0.72
     Monfieur
    -0.67
    Datuak
    -0.66
     ―――――
    -0.65
     متعلقه
    -0.63
     Efq
    -0.63
     itſelf
    -0.61
     Audiodateien
    -0.61
    POSITIVE LOGITS
     AssemblyCulture
    0.59
    k
    0.57
    ((
    0.57
    WindowConstants
    0.56
    GOTREF
    0.55
    s
    0.52
     Exacts
    0.52
    ágeno
    0.51
      
    0.51
    该
    0.51
    Activations Density 0.151%

    No Known Activations