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. 0-GEMMASCOPE-RES-16K
    6. 6292
    Prev
    Next
    INDEX
    Explanations

    specialized terms related to environmental and technical fields, particularly in relation to data, conservation, or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    θρώ
    -0.63
    cmd
    -0.57
    Grüsse
    -0.56
     Schna
    -0.56
     ngào
    -0.54
    leyebilirsiniz
    -0.54
     Assn
    -0.53
     ngang
    -0.52
     Valenzuela
    -0.51
     transférez
    -0.51
    POSITIVE LOGITS
     zirc
    0.69
    WebElementEntity
    0.67
    tro
    0.65
     pinulongan
    0.64
     forState
    0.62
    ChromeDriver
    0.62
    fore
    0.61
    
    0.61
     <=",
    0.60
    Fore
    0.60
    Activations Density 2.755%

    No Known Activations