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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-GEMMASCOPE-RES-16K
    6. 9198
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to material preparation and chemical processes

    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
     Championnat
    -0.42
    setBold
    -0.42
     WIN
    -0.39
     bidding
    -0.38
    $$\
    -0.38
     inclusive
    -0.38
    ざる
    -0.38
     brevet
    -0.38
    Trả
    -0.38
    gewin
    -0.37
    POSITIVE LOGITS
     виправивши
    0.82
     كومونز
    0.79
    TagMode
    0.74
    WillAppear
    0.72
     للمعارف
    0.72
    IntoConstraints
    0.71
     NSCoder
    0.71
    HtmlAttribute
    0.69
    
    0.67
    DockStyle
    0.66
    Activations Density 0.456%

    No Known Activations