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. 7115
    Prev
    Next
    INDEX
    Explanations

    elements related to error handling and importing modules in programming, specifically in Python

    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
     COVID
    -0.89
     Covid
    -0.86
     covid
    -0.85
     TikTok
    -0.77
    covid
    -0.77
     $"{
    -0.76
    Covid
    -0.72
    COVID
    -0.72
    新冠
    -0.68
     pandemic
    -0.67
    POSITIVE LOGITS
     xrange
    1.01
    berdayakan
    0.77
     muß
    0.74
     Arxivat
    0.73
     Archivado
    0.73
    latego
    0.72
    iteritems
    0.71
     Arhivirano
    0.69
     Arquivado
    0.68
     daß
    0.67
    Activations Density 0.147%

    No Known Activations