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. 3-GEMMASCOPE-RES-16K
    6. 11125
    Prev
    Next
    INDEX
    Explanations

    mentions of the CSS display property and its values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parrish
    -0.53
    ท์
    -0.49
     gevolg
    -0.47
     Gruber
    -0.46
    findOrFail
    -0.46
    paro
    -0.45
    står
    -0.44
    Static
    -0.43
    的我
    -0.43
    encana
    -0.43
    POSITIVE LOGITS
    display
    2.08
    Display
    1.40
     display
    1.39
     Display
    1.29
    DISPLAY
    1.27
    setDisplay
    1.08
     DISPLAY
    1.08
    IMPORTED
    0.99
    getDisplay
    0.97
     متعلقه
    0.93
    Activations Density 0.092%

    No Known Activations