© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104184
    Prev
    Next
    INDEX
    Explanations

    specific sports teams and their additional attributes or statistics

    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
     Chwiliwch
    -0.60
     виправивши
    -0.55
    InputBorder
    -0.53
     Infórmanos
    -0.48
     okuyayım
    -0.48
     flows
    -0.47
     ffilmiau
    -0.44
    TypedDataSet
    -0.43
     לכ
    -0.43
    寐
    -0.43
    POSITIVE LOGITS
     Serikat
    0.52
     Nacionales
    0.51
     AppCompatTheme
    0.49
     Clippers
    0.49
     déco
    0.49
     Priester
    0.48
     themſelves
    0.46
    Pyx
    0.46
     Colts
    0.46
     thiếu
    0.45
    Activations Density 0.020%

    No Known Activations