© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 10683
    Prev
    Next
    INDEX
    Explanations

    function calls related to parsing numbers and handling numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.61
     sqlSession
    -0.55
    tamment
    -0.54
     wur
    -0.52
    Zeneca
    -0.49
     Fez
    -0.48
    BagConstraints
    -0.48
    lização
    -0.48
     générations
    -0.48
     ExecuteAsync
    -0.48
    POSITIVE LOGITS
     StringTokenizer
    0.74
     Exacts
    0.64
     يتيمه
    0.61
    WireFormatLite
    0.61
    dataclass
    0.59
    simpleType
    0.59
    Географиясе
    0.57
    клопе
    0.56
    MessageTagHelper
    0.54
    sfw
    0.54
    Activations Density 0.400%

    No Known Activations