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. 15-GEMMASCOPE-RES-16K
    6. 1748
    Prev
    Next
    INDEX
    Explanations

    references to the arXiv preprint repository

    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
    FormTagHelper
    -0.64
    AsUp
    -0.57
    Хьажоргаш
    -0.56
    kháu
    -0.55
     onAnimation
    -0.54
     impressão
    -0.52
     doppio
    -0.52
    ỡ
    -0.52
    msgSender
    -0.50
     архивлан
    -0.50
    POSITIVE LOGITS
    arXiv
    4.71
     arXiv
    1.44
    arxiv
    1.21
     arxiv
    1.06
     EconPapers
    1.00
    Xiv
    0.90
    发表于
    0.89
     Arxiv
    0.84
    Lähteet
    0.76
    /***/
    0.70
    Activations Density 0.005%

    No Known Activations