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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-GEMMASCOPE-RES-16K
    6. 13197
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to Windows and Microsoft APIs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DoubleQuotes
    -0.96
    +#+#
    -0.94
    ArgsConstructor
    -0.93
    ⓧ
    -0.90
     estekak
    -0.88
     cherchés
    -0.87
    RegressionTest
    -0.85
    fromnode
    -0.85
    EDEFAULT
    -0.85
     للاسماء
    -0.84
    POSITIVE LOGITS
    Xaml
    0.97
     Microsoft
    0.95
    Microsoft
    0.90
     Windows
    0.88
    Windows
    0.84
    microsoft
    0.75
     microsoft
    0.75
    HRESULT
    0.71
    windows
    0.70
     SharePoint
    0.68
    Activations Density 0.496%

    No Known Activations