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. 103006
    Prev
    Next
    INDEX
    Explanations

    technical specifications and measurements related to scientific experiments

    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
     Among
    -0.31
     device
    -0.31
    b
    -0.29
    num
    -0.28
     among
    -0.28
    rib
    -0.27
     ح
    -0.27
    array
    -0.27
    Among
    -0.27
     WAS
    -0.26
    POSITIVE LOGITS
    новништво
    0.77
     nahilalakip
    0.74
    setVerticalGroup
    0.73
     autorytatywna
    0.72
     AssemblyTitle
    0.69
    posedge
    0.69
     queſta
    0.69
     AssemblyVersion
    0.69
    bootstrapcdn
    0.69
    NewUrlParser
    0.68
    Activations Density 0.379%

    No Known Activations