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. 13967
    Prev
    Next
    INDEX
    Explanations

    statements related to legal or financial issues

    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
    ftagPool
    -0.58
     almost
    -0.57
     Almost
    -0.56
    almost
    -0.53
    意外と
    -0.53
     cheap
    -0.52
     måske
    -0.52
     sneaky
    -0.52
     screamed
    -0.52
    Almost
    -0.51
    POSITIVE LOGITS
    verständlich
    0.82
     neceff
    0.82
    eraard
    0.81
     fubject
    0.80
     Majefty
    0.79
     neceffary
    0.77
     ſeveral
    0.76
     naturlig
    0.74
     regrettable
    0.74
     itſelf
    0.74
    Activations Density 0.271%

    No Known Activations