Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 6714
    Prev
    Next
    INDEX
    Explanations

    financial terms related to fixed income securities and municipal bonds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unhofer
    -0.54
    IMPORTED
    -0.53
     ro
    -0.48
     ве
    -0.46
     Sho
    -0.46
    ArgumentParser
    -0.46
     Guild
    -0.45
    heber
    -0.45
     Das
    -0.45
    Poppins
    -0.44
    POSITIVE LOGITS
     bond
    0.96
     bonds
    0.90
    bond
    0.78
     Bonds
    0.77
    Bond
    0.74
     issuance
    0.69
     Bond
    0.69
    bonds
    0.68
     refinance
    0.68
     refinancing
    0.67
    Activations Density 0.099%

    No Known Activations