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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73559
    Prev
    Next
    INDEX
    Explanations

    events and social gatherings involving mingling and interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    xdr
    -0.44
    ViewImports
    -0.40
    MathML
    -0.39
    OPA
    -0.38
     LT
    -0.37
    live
    -0.36
    loped
    -0.36
     ant
    -0.35
    metido
    -0.35
     rem
    -0.35
    POSITIVE LOGITS
     للمعارف
    0.52
     Italijani
    0.47
     DevComponents
    0.47
    ampingi
    0.47
    onOptions
    0.45
    izontal
    0.45
    AllowUser
    0.45
     corridors
    0.44
     hallways
    0.43
     pretrial
    0.43
    Activations Density 0.025%

    No Known Activations