© 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. 16-GEMMASCOPE-RES-16K
    6. 12931
    Prev
    Next
    INDEX
    Explanations

    financial and transactional terms, particularly focusing on numbers and currency symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.60
    %"),
    -0.56
    +#+#
    -0.55
    TagMode
    -0.48
    twimg
    -0.48
     FetchType
    -0.47
    HasAnnotation
    -0.47
    ArrowToggle
    -0.47
    Revenir
    -0.46
     springfox
    -0.45
    POSITIVE LOGITS
    source
    0.95
     source
    0.77
    Source
    0.73
     Source
    0.60
     SOURCE
    0.58
    SOURCE
    0.57
    getSource
    0.57
    Sources
    0.56
    sources
    0.56
     fuente
    0.52
    Activations Density 0.007%

    No Known Activations