© 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. 33-GEMMASCOPE-RES-16K
    11. 1959
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic trends and changes in financial data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    近期
    -0.68
     चीज़ों
    -0.66
     recently
    -0.66
     Recently
    -0.65
    Recently
    -0.65
    近日
    -0.63
    recently
    -0.63
    Recent
    -0.60
     Recent
    -0.59
     lately
    -0.59
    POSITIVE LOGITS
     last
    2.25
    last
    1.71
    Last
    1.57
     Last
    1.53
     LAST
    1.45
     förra
    1.44
     laſt
    1.39
    去年
    1.37
     laft
    1.36
     прошлого
    1.35
    Activations Density 0.377%

    No Known Activations