© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8840
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their roles within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     resourceCulture
    -0.62
    MigrationBuilder
    -0.57
    WEBPACK
    -0.56
    TagMode
    -0.53
    SequentialGroup
    -0.52
     queſto
    -0.52
    StoryboardSegue
    -0.52
     Volt
    -0.50
    adaptiveStyles
    -0.50
    blos
    -0.49
    POSITIVE LOGITS
     CEO
    0.48
     руководи
    0.46
     officials
    0.46
     spokesman
    0.45
     chairman
    0.44
     Chairman
    0.42
    Director
    0.41
     chief
    0.41
    director
    0.40
     spokesperson
    0.40
    Activations Density 0.215%

    No Known Activations