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. 5-GEMMASCOPE-RES-16K
    6. 12038
    Prev
    Next
    INDEX
    Explanations

    entries related to screen customization and settings for mobile devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.81
    ArgsConstructor
    -0.73
    GenerationType
    -0.67
    তথ্যসূত্র
    -0.65
    CPtr
    -0.62
     विश्वसनीयता
    -0.59
    ďaka
    -0.58
    fml
    -0.57
    struktion
    -0.57
    WaitGroup
    -0.57
    POSITIVE LOGITS
     wallpaper
    0.84
     Wallpaper
    0.72
     wallpapers
    0.70
    Wallpaper
    0.64
     Desktop
    0.63
    MigrationBuilder
    0.61
     Wallpapers
    0.55
     desktop
    0.54
    Desktop
    0.51
    ίσ
    0.49
    Activations Density 0.345%

    No Known Activations