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. 20-GEMMASCOPE-RES-16K
    6. 10763
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and user-friendly features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after "a [something]" or "[someone] clicks"

    np_acts-logits-general · gemini-2.0-flash

    quick action or event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagHelper
    -0.77
    ViewImports
    -0.71
    WebElementEntity
    -0.70
    UnitTesting
    -0.65
     "]";
    -0.63
     Lightboxes
    -0.63
    TagMode
    -0.63
     CascadeType
    -0.62
    ⓧ
    -0.62
    interopRequire
    -0.62
    POSITIVE LOGITS
     click
    1.22
     clicks
    1.02
     flick
    1.01
     snap
    0.98
    click
    0.96
     klik
    0.94
     blink
    0.88
    Click
    0.85
     instant
    0.82
     Click
    0.81
    Activations Density 0.143%

    No Known Activations