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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6913
    Prev
    Next
    INDEX
    Explanations

    experiences and sentiments related to learning and practicing sewing skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    目前
    -0.80
     currently
    -0.78
     derzeit
    -0.76
     đang
    -0.74
     momentan
    -0.73
     bisher
    -0.70
     recent
    -0.70
     Currently
    -0.68
    目前的
    -0.67
     aktuell
    -0.66
    POSITIVE LOGITS
    那时候
    1.17
    当時は
    1.02
     помню
    1.01
    那时
    0.97
     damals
    0.96
     damal
    0.93
     vroeger
    0.91
     summers
    0.90
    当时的
    0.87
     damaligen
    0.84
    Activations Density 0.275%

    No Known Activations