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. 11039
    Prev
    Next
    INDEX
    Explanations

    references to Colombian locations and institutions related to education and culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Colombia/Colombian football and politics

    np_acts-logits-general · gemini-2.0-flash

    colombia and its cities

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    contentLoaded
    -0.81
     Diputados
    -0.63
    Зноскі
    -0.61
    reuth
    -0.58
    انيف
    -0.58
    脚注の使い方
    -0.56
    طبيق
    -0.56
    তথ্যসূত্র
    -0.55
    IUrlHelper
    -0.55
     Perak
    -0.54
    POSITIVE LOGITS
     Colombia
    0.79
     Colombian
    0.76
     Osp
    0.70
     peace
    0.67
    oquia
    0.65
    ooga
    0.63
    Colombia
    0.63
     Medellín
    0.63
     Bogotá
    0.63
     Cali
    0.62
    Activations Density 0.104%

    No Known Activations