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-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1004
    Prev
    Next
    INDEX
    Explanations

    descriptive terms that relate to shapes and their characteristics

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

    rounded shapes and modifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.56
    writerow
    -0.49
    scrapy
    -0.47
    Хьажоргаш
    -0.46
     Præ
    -0.46
     ocul
    -0.45
     getField
    -0.45
    郎
    -0.45
    scryfall
    -0.45
     []:
    -0.45
    POSITIVE LOGITS
     Rounded
    0.73
     rounded
    0.63
    homa
    0.57
    rounded
    0.54
    wellness
    0.54
     Rugged
    0.54
     zacht
    0.52
     StatelessWidget
    0.52
    Rounded
    0.52
     Fuller
    0.52
    Activations Density 0.014%

    No Known Activations