© 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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 13078
    Prev
    Next
    INDEX
    Explanations

    instances of the word "exposure" and related terms regarding exposure to various conditions or factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kitch
    -0.93
     GenerationType
    -0.92
     Kitt
    -0.90
    awtextra
    -0.88
    chossen
    -0.82
     AssemblyCulture
    -0.82
    ownic
    -0.80
     OneNote
    -0.79
     Siti
    -0.79
    WEBPACK
    -0.79
    POSITIVE LOGITS
    erweise
    0.72
    ‾
    0.69
     exposure
    0.68
    properly
    0.65
    exposure
    0.65
     properly
    0.65
     Exposure
    0.65
    maßen
    0.64
     Menge
    0.64
    Exposure
    0.63
    Activations Density 0.172%

    No Known Activations