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. 45624
    Prev
    Next
    INDEX
    Explanations

    references to family-friendly content and activities

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

    family and related activities

    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
    SharedDtor
    -0.60
     Paglinawan
    -0.59
    Tembelea
    -0.59
    haikusbot
    -0.51
    utilisons
    -0.51
     intStringLen
    -0.50
    colgante
    -0.49
    parsedMessage
    -0.48
    VYMaps
    -0.48
    مقاله
    -0.47
    POSITIVE LOGITS
    Family
    0.65
     family
    0.63
    family
    0.63
     families
    0.63
     rodzin
    0.60
     familles
    0.58
    Families
    0.57
    👪
    0.57
    FAMILY
    0.57
     keluarga
    0.56
    Activations Density 0.003%

    No Known Activations