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. 16-GEMMASCOPE-RES-16K
    6. 5110
    Prev
    Next
    INDEX
    Explanations

    details related to supplementary material and appendices in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    supplementary materials like appendices and attachments

    np_acts-logits-general · gemini-2.0-flash

    supplementary appendices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.78
    Rüyada
    -0.78
     initComponents
    -0.74
    queryInterface
    -0.72
    msgSender
    -0.71
    Бахар
    -0.71
    opsida
    -0.69
    +#+#
    -0.69
     vPvB
    -0.67
     TestBed
    -0.66
    POSITIVE LOGITS
     appendix
    1.03
    appendix
    0.85
     Appendix
    0.84
     appendices
    0.82
     attached
    0.77
     attachments
    0.76
     attachment
    0.75
     appended
    0.74
     accompanying
    0.72
    Appendix
    0.71
    Activations Density 1.155%

    No Known Activations