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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 14484
    Prev
    Next
    INDEX
    Explanations

    key elements related to UI components and their properties in user interface programming

    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
    ]--;
    -0.86
    исленность
    -0.76
    "],
    
    -0.74
    InitVars
    -0.72
    ftagPool
    -0.71
     समीक्षक
    -0.71
    انتهای
    -0.71
    ]++;
    -0.69
    帖最后由
    -0.69
     CreateTagHelper
    -0.69
    POSITIVE LOGITS
    title
    0.60
     title
    0.58
    ylabel
    0.55
     getString
    0.52
     "
    0.52
     getTitle
    0.50
     getResources
    0.50
    LocalizedString
    0.49
     "¿
    0.49
     says
    0.48
    Activations Density 0.194%

    No Known Activations