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. 20-GEMMASCOPE-RES-16K
    6. 14006
    Prev
    Next
    INDEX
    Explanations

    quantitative expressions related to dates and times, including numerical values and schedules

    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
    ighborhood
    -0.67
     neighborhood
    -0.60
    neighborhood
    -0.57
    Portály
    -0.56
    addCriterion
    -0.56
    principalTable
    -0.54
     FAVOR
    -0.53
    capitalize
    -0.52
     Harbor
    -0.51
     favor
    -0.51
    POSITIVE LOGITS
    RetentionPolicy
    0.65
     Réponses
    0.62
     referenties
    0.60
     doInBackground
    0.60
     @"/
    0.59
     BoxFit
    0.58
    abspath
    0.55
    الإنجليزية
    0.54
    £
    0.54
    ReusableCell
    0.54
    Activations Density 0.118%

    No Known Activations