Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2017
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, indicating the end of sentences or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Földrajzportál
    -0.47
     corps
    -0.44
    ContentAlignment
    -0.44
    ItemBackground
    -0.44
    endregion
    -0.43
     via
    -0.43
    theoremstyle
    -0.43
     Semi
    -0.43
    的好
    -0.41
    çi
    -0.41
    POSITIVE LOGITS
     ddelweddau
    0.98
     numberWith
    0.78
    tagHelperRunner
    0.75
     EconPapers
    0.70
     AssemblyCompany
    0.69
     متعلقه
    0.66
     CreateTagHelper
    0.65
    espo
    0.65
     noDo
    0.65
    CloseOperation
    0.64
    Activations Density 0.029%

    No Known Activations