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. 1222
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to loops and conditional statements

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

    captain Paul, inhibit density, symptom of

    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
     transfieras
    -0.60
     للمعارف
    -0.59
     محفوظة
    -0.54
    Obrázky
    -0.52
     utafitiHapana
    -0.50
     externi
    -0.50
     surla
    -0.49
     arşivlendi
    -0.47
     himo
    -0.47
     autorytatywna
    -0.45
    POSITIVE LOGITS
    autoconfigure
    0.41
    quias
    0.34
    ViewImports
    0.33
     certiorari
    0.32
    parsedMessage
    0.31
    Семья
    0.31
    PRNewswire
    0.30
     useRouter
    0.30
    Kunden
    0.29
     PhpStorm
    0.29
    Activations Density 0.008%

    No Known Activations