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. 9-GEMMASCOPE-RES-16K
    6. 15421
    Prev
    Next
    INDEX
    Explanations

    references to supplementary materials or appendices in scholarly texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.74
    Бахар
    -0.61
    extAlignment
    -0.61
    GeneratedValue
    -0.60
    +#+#
    -0.60
     HomeController
    -0.59
    ladiator
    -0.59
    jewództ
    -0.58
    髦
    -0.58
     queima
    -0.56
    POSITIVE LOGITS
    appendix
    1.06
     appendix
    1.01
     Appendix
    0.91
    Appendix
    0.91
     appendices
    0.87
     Appendices
    0.75
     annex
    0.72
    APPENDIX
    0.71
     Anhang
    0.70
    Anexo
    0.70
    Activations Density 0.556%

    No Known Activations