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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 3599
    Prev
    Next
    INDEX
    Explanations

    monetary values and pricing details

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

    price and cost figures

    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
    GEBURTSDATUM
    -0.50
    OGND
    -0.49
     jScrollPane
    -0.48
    parsedMessage
    -0.45
    :✨
    -0.40
    دانشنامهٔ
    -0.39
    expandindo
    -0.38
    strijden
    -0.38
    WaitGroup
    -0.38
     hacked
    -0.38
    POSITIVE LOGITS
     price
    0.85
     prices
    0.81
    price
    0.78
     pricing
    0.77
     priced
    0.73
    prices
    0.72
    Prices
    0.71
     getPrice
    0.70
    Price
    0.70
     harganya
    0.67
    Activations Density 0.017%

    No Known Activations