© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10428
    Prev
    Next
    INDEX
    Explanations

    references to fraudulent activities involving passports

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

    Fake documents or identities

    np_acts-logits-general · gemini-2.0-flash

    fake identity documents and fraud

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lát
    -0.34
    벅
    -0.33
    口水
    -0.33
     Werbung
    -0.33
     objek
    -0.32
     sucul
    -0.32
     Putih
    -0.31
    ductos
    -0.31
     lược
    -0.31
    FunctionFlags
    -0.31
    POSITIVE LOGITS
     forgery
    0.84
     fraud
    0.69
     Faker
    0.65
     fakes
    0.63
     fraudulent
    0.62
    Fraud
    0.61
     counterfe
    0.61
     fraudul
    0.60
     faking
    0.60
     fake
    0.60
    Activations Density 0.512%

    No Known Activations