© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10150
    Prev
    Next
    INDEX
    Explanations

    references to actions or events occurring "on" specific topics or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "on" followed by "the."

    np_acts-logits-general · gemini-2.0-flash

    on the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppMethod
    -0.50
     propOrder
    -0.50
    getWriter
    -0.49
     jsPsych
    -0.45
    Activités
    -0.44
    ➟
    -0.44
    twimg
    -0.43
    MigrationBuilder
    -0.43
     AssemblyProduct
    -0.42
    retudo
    -0.42
    POSITIVE LOGITS
     on
    0.86
    บน
    0.66
     trên
    0.66
     aboard
    0.65
     On
    0.63
     روی
    0.62
     onboard
    0.59
     auf
    0.59
     ON
    0.57
    feinander
    0.56
    Activations Density 0.475%

    No Known Activations