© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 7660
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate thoroughness or completeness in research or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.70
    styleType
    -0.64
    ValueStyle
    -0.63
    GEBURTSDATUM
    -0.58
     AssemblyProduct
    -0.57
     estekak
    -0.57
    tonode
    -0.56
     yaiba
    -0.54
    SqlClient
    -0.52
     للاسماء
    -0.52
    POSITIVE LOGITS
     compact
    0.93
     comprehensive
    0.85
     Comprehensive
    0.82
    compact
    0.81
    Comprehensive
    0.77
    comprehensive
    0.75
     Compact
    0.75
     pack
    0.72
     comprehensively
    0.67
    Compact
    0.66
    Activations Density 0.194%

    No Known Activations