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. 13743
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface interactions, particularly button click events in programming code

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

    user interface actions and elements

    np_acts-logits-general · gemini-2.0-flash

    UI element interaction

    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
    expandindo
    -1.20
     חיצוניים
    -0.84
     Italijanski
    -0.81
    +#+#
    -0.80
    principalTable
    -0.79
    المناصب
    -0.79
    MessageOf
    -0.78
    rungsseite
    -0.77
    تقاوى
    -0.76
    ьаж
    -0.76
    POSITIVE LOGITS
    View
    0.88
     View
    0.79
     view
    0.77
    view
    0.73
    OnClickListener
    0.69
     views
    0.64
     click
    0.60
     clicked
    0.60
     VIEW
    0.59
     clicks
    0.58
    Activations Density 0.029%

    No Known Activations