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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4452
    Prev
    Next
    INDEX
    Explanations

    terms related to anti-money laundering and financial crime prevention

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

    Anti-money laundering or government policy

    np_acts-logits-general · gemini-2.0-flash

    anti-money laundering investigations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.57
    DockStyle
    -0.56
     isSet
    -0.55
    Portail
    -0.55
     BrowserRouter
    -0.54
    Spoljašnje
    -0.54
    setVerticalGroup
    -0.54
     الحره
    -0.53
     charset
    -0.51
    kuuta
    -0.50
    POSITIVE LOGITS
    enumii
    0.73
     AML
    0.71
     laundering
    0.64
     launder
    0.62
     convicted
    0.60
    enumi
    0.60
     Anti
    0.59
     sanctions
    0.59
     anti
    0.57
    AML
    0.56
    Activations Density 0.182%

    No Known Activations