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. 0-GEMMASCOPE-RES-16K
    6. 3427
    Prev
    Next
    INDEX
    Explanations

    temporal references and frequencies related to medical treatments and studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -1.01
     disambiguazione
    -0.87
     onCreateView
    -0.81
     للمعارف
    -0.81
    WebServlet
    -0.80
    IsContent
    -0.79
     שוליים
    -0.79
    thâu
    -0.79
     valmis
    -0.76
    ArgsConstructor
    -0.76
    POSITIVE LOGITS
    testng
    0.59
    MONTH
    0.56
     monthly
    0.53
    Month
    0.52
     month
    0.51
     hourly
    0.51
    年
    0.51
    mius
    0.51
    week
    0.51
    кру
    0.51
    Activations Density 0.448%

    No Known Activations