Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 64762
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to scientific and academic subjects

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

    technical concepts followed by grammatical markers

    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
     mijne
    -0.35
    互联网档案馆
    -0.32
     scoper
    -0.31
     sosp
    -0.31
     koke
    -0.29
    cakup
    -0.29
    ben
    -0.29
     adopción
    -0.28
     kode
    -0.28
     unpublished
    -0.27
    POSITIVE LOGITS
     informée
    0.73
     NSCoder
    0.67
     AssemblyCompany
    0.64
     للاسماء
    0.61
    MLLoader
    0.60
    ----</
    0.57
    StoryboardSegue
    0.56
     defaultstate
    0.54
    AnimationsModule
    0.54
     InputDecoration
    0.52
    Activations Density 0.094%

    No Known Activations