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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2284
    Prev
    Next
    INDEX
    Explanations

    terms related to anti-money laundering and regulatory compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.66
    initializeApp
    -0.57
    ouac
    -0.55
    setVerticalGroup
    -0.54
    RegressionTest
    -0.53
     يتيمه
    -0.53
     ProtoMessage
    -0.53
    Попис
    -0.53
    Spoljašnje
    -0.52
     Gettysburg
    -0.50
    POSITIVE LOGITS
     offshore
    0.69
    enumi
    0.66
     laundering
    0.65
     launder
    0.65
     FAT
    0.65
     SWIFT
    0.62
     international
    0.60
     Foreign
    0.60
     Offshore
    0.59
     AML
    0.58
    Activations Density 0.234%

    No Known Activations