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. 16-GEMMASCOPE-RES-16K
    6. 3039
    Prev
    Next
    INDEX
    Explanations

    syntactic patterns associated with event handling in programming code

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

    `.` followed by `preventDefault` or `Nodes`

    np_acts-logits-general · gemini-2.0-flash

    prevent default event behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.76
    Referències
    -0.66
    RenderAtEndOf
    -0.61
    Personendaten
    -0.57
    writeFieldEnd
    -0.55
    存于互联网档案馆
    -0.55
    Produzione
    -0.54
    addCriterion
    -0.54
    Przypisy
    -0.52
     prestazioni
    -0.51
    POSITIVE LOGITS
     provisional
    0.65
     Gaulle
    0.57
    IsContent
    0.54
    SEGUIR
    0.53
    culum
    0.52
    owiak
    0.52
     BRARY
    0.51
    cửa
    0.51
    iffion
    0.51
     FormGroup
    0.50
    Activations Density 0.103%

    No Known Activations