© 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-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5567
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and operations often used in scientific formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     برانيه
    -0.50
     arbete
    -0.42
     تضيفلها
    -0.41
     magát
    -0.40
    jewództ
    -0.40
    SceneManagement
    -0.39
     legyen
    -0.39
    beitrag
    -0.37
    takings
    -0.37
    chemia
    -0.37
    POSITIVE LOGITS
    ^{-
    1.27
    }^{-
    1.19
    )^{-
    1.02
     ^{-
    0.99
    ]^{-
    0.94
     }^{-
    0.93
    ^{-\
    0.86
    ^(-
    0.72
    ^{-}
    0.68
    ^-
    0.68
    Activations Density 0.621%

    No Known Activations