Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 5762
    Prev
    Next
    INDEX
    Explanations

    phrases and questions related to calculations and mathematical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     independently
    -0.52
    Biography
    -0.44
     override
    -0.42
    thus
    -0.42
    march
    -0.42
    Financi
    -0.42
    ViewImports
    -0.42
     trumps
    -0.42
     ira
    -0.41
    fre
    -0.41
    POSITIVE LOGITS
    ⓧ
    1.01
    RegistryLite
    0.82
     Италијани
    0.77
     تضيفلها
    0.75
     مشين
    0.69
     kasarigan
    0.69
     Italijanski
    0.68
     Réponses
    0.66
     initComponents
    0.64
    queryInterface
    0.64
    Activations Density 0.888%

    No Known Activations