© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 11351
    Prev
    Next
    INDEX
    Explanations

    references to the 'Win' operating system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    tangentMode
    -0.75
     Mahomet
    -0.71
    "}")
    -0.70
    }();
    -0.66
     Ogden
    -0.66
     resourceCulture
    -0.65
    Newark
    -0.65
     Magdeburg
    -0.65
     Daher
    -0.65
     itſelf
    -0.64
    POSITIVE LOGITS
     Win
    2.97
    Win
    2.96
    win
    2.92
     win
    2.76
     WIN
    2.50
    WIN
    2.47
     Wins
    1.74
    Wins
    1.70
     wins
    1.61
    wins
    1.55
    Activations Density 0.031%

    No Known Activations