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. 10575
    Prev
    Next
    INDEX
    Explanations

    different forms and properties of display elements in technical contexts

    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
     GenerationType
    -1.00
     rêver
    -0.90
    슷
    -0.90
     estimés
    -0.86
     hâte
    -0.84
    المناصب
    -0.83
     cuaderno
    -0.82
     Normdatei
    -0.81
     Kopp
    -0.80
     situés
    -0.80
    POSITIVE LOGITS
     display
    2.33
     displays
    2.23
     Display
    2.20
     DISPLAY
    2.15
     Displays
    2.04
    Display
    2.02
    displays
    2.01
    display
    1.95
    Displays
    1.93
     displaying
    1.90
    Activations Density 0.045%

    No Known Activations