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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 58415
    Prev
    Next
    INDEX
    Explanations

    elements related to code and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ọi
    -0.52
    noz
    -0.46
     AssemblyCompany
    -0.42
     Attra
    -0.42
    τεύ
    -0.41
    Extended
    -0.40
    fill
    -0.40
    typeparam
    -0.39
     Amal
    -0.39
    lak
    -0.38
    POSITIVE LOGITS
    出版年
    0.90
    RegistryLite
    0.85
    انجليز
    0.84
    djangoproject
    0.78
     تضيفلها
    0.77
    oredCriteria
    0.77
    ArrowToggle
    0.73
    WriteTagHelper
    0.72
    thâu
    0.71
    apimachinery
    0.70
    Activations Density 0.247%

    No Known Activations