© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 2431
    Prev
    Next
    INDEX
    Explanations

    words related to tabs and tabulation in a user interface context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.72
     betweenstory
    -0.70
    VYMaps
    -0.65
    fromnode
    -0.59
    AndEndTag
    -0.57
     indígen
    -0.56
     inflación
    -0.56
    rungsseite
    -0.56
     ویکی‌پدی
    -0.55
    Personendaten
    -0.55
    POSITIVE LOGITS
     tab
    0.95
    Tab
    0.86
     Tab
    0.84
     tabs
    0.81
    language
    0.78
     insurance
    0.73
    tab
    0.71
     Tabs
    0.70
     language
    0.70
    Tabs
    0.69
    Activations Density 0.198%

    No Known Activations