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. 91551
    Prev
    Next
    INDEX
    Explanations

    topics related to scientific studies and experiments under varying conditions, particularly atmospheric and hydrostatic pressure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    SharedCtor
    -0.65
    UrlResolution
    -0.65
     الحره
    -0.64
    MLLoader
    -0.60
    MessageTagHelper
    -0.59
    IntoConstraints
    -0.58
    principalTable
    -0.57
     Italijani
    -0.57
     Italijanski
    -0.57
     للمعارف
    -0.56
    POSITIVE LOGITS
    StatusBar
    0.33
     exposure
    0.31
    zip
    0.31
    ်
    0.30
     altitude
    0.30
     travelling
    0.29
     experience
    0.29
    NULL
    0.28
     Sagan
    0.28
     travel
    0.28
    Activations Density 0.139%

    No Known Activations