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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8769
    Prev
    Next
    INDEX
    Explanations

    references to operating systems, specifically Windows and Linux

    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
     noDo
    -0.45
     esimer
    -0.44
     hyö
    -0.43
     ribs
    -0.42
    GHIJKLM
    -0.41
     tää
    -0.40
     fallu
    -0.40
     tästä
    -0.39
     mukaan
    -0.39
     scratches
    -0.39
    POSITIVE LOGITS
    Window
    2.36
     Window
    1.91
    window
    1.52
     Windows
    1.47
     WINDOW
    1.33
    Windows
    1.32
    WINDOW
    1.26
    getWindow
    1.16
     window
    1.15
    GetWindow
    0.98
    Activations Density 0.086%

    No Known Activations