© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2059
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical or demographic data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.80
    </thead>
    -0.62
     للاسماء
    -0.57
    ंदीखरीदारी
    -0.57
     ویکی‌پدی
    -0.54
    出版年
    -0.53
     שוליים
    -0.53
     telt
    -0.52
     betweenstory
    -0.52
     상세
    -0.48
    POSITIVE LOGITS
    整个
    0.95
     entire
    0.95
     whole
    0.89
     overall
    0.85
    整個
    0.85
     wider
    0.85
    entire
    0.82
    whole
    0.80
     broader
    0.78
     gesamte
    0.74
    Activations Density 0.341%

    No Known Activations