© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5692
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial agreements and transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    financial transactions/banking

    np_acts-logits-general · gemini-2.0-flash

    Banco Rural withdrawals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ISNI
    -0.61
     commerciali
    -0.52
     destruction
    -0.47
     mathematicians
    -0.45
     destroys
    -0.45
    setLevel
    -0.44
    versies
    -0.44
    原始内容存档于
    -0.43
     fishermen
    -0.43
     flushing
    -0.43
    POSITIVE LOGITS
     liquid
    0.61
     fact
    0.61
     Gast
    0.60
    RegressionTest
    0.59
    Gast
    0.58
     Inversion
    0.57
     Cob
    0.56
    Cob
    0.56
     Pag
    0.55
     inversion
    0.54
    Activations Density 0.032%

    No Known Activations