© 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. 15-GEMMASCOPE-RES-16K
    6. 8061
    Prev
    Next
    INDEX
    Explanations

    patterns and references related to numerical values and formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.73
    ]**
    -0.62
    ")[
    -0.58
    IsContent
    -0.57
    heça
    -0.56
    Ends
    -0.56
    MemoryWarning
    -0.55
    شاف
    -0.55
     متعلقه
    -0.55
    ptonshire
    -0.55
    POSITIVE LOGITS
     numbers
    1.18
     numeric
    0.95
     number
    0.92
     Numer
    0.91
    numbers
    0.90
     NUMBERS
    0.90
     digits
    0.87
     numerical
    0.87
     numeral
    0.86
     Numbers
    0.86
    Activations Density 0.868%

    No Known Activations