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. 20-GEMMASCOPE-RES-131K
    6. 22464
    Prev
    Next
    INDEX
    Explanations

    fields related to names in a data structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Slf
    -0.62
     Taktlose
    -0.50
    AndFlush
    -0.48
    AnimationsModule
    -0.47
    ⃣
    -0.46
    ymce
    -0.45
     nahilalakip
    -0.45
    存于互联网档案馆
    -0.43
     informée
    -0.43
     Мексичка
    -0.41
    POSITIVE LOGITS
     AssemblyVersion
    0.64
    technologies
    0.59
     ſind
    0.59
    ouna
    0.57
    nologies
    0.56
     leſs
    0.55
     DuPont
    0.55
     Bengaluru
    0.55
     iſt
    0.54
    FORMAN
    0.53
    Activations Density 0.018%

    No Known Activations