© 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. 3-GEMMASCOPE-RES-16K
    6. 5205
    Prev
    Next
    INDEX
    Explanations

    references to the Mac or macOS

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    computer
    -0.95
     computer
    -0.93
     Computer
    -0.87
    Computer
    -0.87
     Computers
    -0.81
     computers
    -0.80
    computers
    -0.80
    Computers
    -0.76
    COMPUTER
    -0.71
     komputer
    -0.68
    POSITIVE LOGITS
     Mac
    1.31
     mac
    1.27
    Mac
    1.22
    mac
    1.05
     MAC
    0.94
     topping
    0.94
     topped
    0.92
    MAC
    0.88
    topping
    0.73
    EndContext
    0.72
    Activations Density 0.056%

    No Known Activations