© 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. 5734
    Prev
    Next
    INDEX
    Explanations

    function calls related to numerical parsing

    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
     nullptr
    -0.61
    Обе
    -0.57
    ⓧ
    -0.56
     Kool
    -0.55
    chtig
    -0.54
    伎
    -0.53
    ostar
    -0.53
    makeConstraints
    -0.53
    ddots
    -0.52
    > 
    -0.50
    POSITIVE LOGITS
    parseInt
    2.67
     parseInt
    2.27
    parseLong
    1.59
    parseDouble
    1.52
    parseFloat
    1.52
     parseFloat
    1.35
    parsedMessage
    0.93
     AssemblyTitle
    0.88
     atoi
    0.81
    SerializedName
    0.80
    Activations Density 0.019%

    No Known Activations