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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 53483
    Prev
    Next
    INDEX
    Explanations

    concerns related to indoor air quality and allergens

    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
    szy
    -0.37
    sstelle
    -0.35
     Stam
    -0.35
    insch
    -0.34
    
    -0.32
     ghi
    -0.31
     Jos
    -0.31
    öt
    -0.31
     trò
    -0.30
    临
    -0.30
    POSITIVE LOGITS
     indoor
    0.69
    indoor
    0.63
    IsContent
    0.63
    Indoor
    0.63
     Indoor
    0.63
    windowFixed
    0.62
     indoors
    0.59
    XmlAccessType
    0.57
    ftagPool
    0.56
     myſelf
    0.56
    Activations Density 0.020%

    No Known Activations