© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4545
    Prev
    Next
    INDEX
    Explanations

    terms associated with financial concepts and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 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
     său
    -0.51
    inguém
    -0.49
    — 
    -0.48
     artesanal
    -0.48
     stubborn
    -0.47
     pungent
    -0.46
     Trường
    -0.45
     rép
    -0.45
    Rhestr
    -0.45
    Pup
    -0.43
    POSITIVE LOGITS
     Financial
    0.93
    Finance
    0.92
     Finance
    0.92
    Financial
    0.91
     Financi
    0.91
    financial
    0.88
     FINANCE
    0.88
     finance
    0.87
     FINANCIAL
    0.86
     financial
    0.86
    Activations Density 0.092%

    No Known Activations