© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 54034
    Prev
    Next
    INDEX
    Explanations

    mentions of websites or online resources

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

    website links and sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     enamorado
    -0.50
     Terbaik
    -0.43
     eccell
    -0.42
     cielos
    -0.41
     Tasche
    -0.41
     näytte
    -0.41
     mukana
    -0.41
     romántico
    -0.40
     olvido
    -0.40
     Italij
    -0.39
    POSITIVE LOGITS
     informée
    0.71
    sizeCache
    0.70
     otomatig
    0.67
    Rhestr
    0.66
    ंदीखरीदारी
    0.66
     Italijanski
    0.66
    :✨
    0.65
    adaptiveStyles
    0.63
    IUrlHelper
    0.62
    ThemeOverlay
    0.62
    Activations Density 0.030%

    No Known Activations