© 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
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 60
    Prev
    Next
    INDEX
    Explanations

    terms related to import and export activities

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

    Importing and exporting goods and data

    np_acts-logits-general · gemini-2.0-flash

    import and export of goods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setOnAction
    -0.52
    DBNull
    -0.51
    JUnit
    -0.49
    inguém
    -0.46
    elif
    -0.45
     DBNull
    -0.45
    Où
    -0.42
     GameManager
    -0.42
    s
    -0.42
     anello
    -0.42
    POSITIVE LOGITS
     Export
    0.84
    Export
    0.80
     Import
    0.79
     imports
    0.77
    IMPORTED
    0.76
     Imports
    0.76
     export
    0.75
     Imported
    0.75
     Importing
    0.75
    Imported
    0.73
    Activations Density 0.158%

    No Known Activations