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. 5-GEMMASCOPE-RES-16K
    6. 11668
    Prev
    Next
    INDEX
    Explanations

    terms related to "principal" and "principal component analysis."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Оно
    -0.74
     Вікі
    -0.72
    ed
    -0.71
    Krie
    -0.67
     Кубка
    -0.67
     Bergamo
    -0.67
     Leck
    -0.66
    ︎
    -0.66
     complémentaires
    -0.66
     Bany
    -0.66
    POSITIVE LOGITS
     principal
    1.65
     PRINCIPAL
    1.61
    principal
    1.59
     Principal
    1.59
    Principal
    1.58
     principals
    1.07
     Principals
    1.03
    cipal
    0.99
    princip
    0.97
    ant
    0.91
    Activations Density 0.122%

    No Known Activations