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 Post
    5. 12-GEMMASCOPE-RES-1M
    6. 493
    Prev
    Next
    INDEX
    Explanations

    concepts related to light and illumination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vra
    -0.61
    jek
    -0.51
     ആ
    -0.50
    ien
    -0.50
    __':
    -0.50
     ఆ
    -0.48
     ಆ
    -0.47
    Biographical
    -0.47
     labios
    -0.47
    wier
    -0.47
    POSITIVE LOGITS
     Мексичка
    0.82
     виправивши
    0.77
    hilation
    0.74
    PreferredItem
    0.73
    клопе
    0.73
    цездатний
    0.72
     daylight
    0.70
    aarrggbb
    0.69
     autorytatywna
    0.69
     SwitchCompat
    0.68
    Activations Density 0.000%

    No Known Activations