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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 43361
    Prev
    Next
    INDEX
    Explanations

    references to scams and fraudulent activities

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

    scam, fraud, con, hoax, scheme

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    weiss
    -0.40
     bahç
    -0.40
     accol
    -0.39
    <>
    -0.38
     nevoie
    -0.38
     geleverd
    -0.38
    Rath
    -0.38
     permissive
    -0.37
     necessary
    -0.37
     favorable
    -0.36
    POSITIVE LOGITS
     scam
    1.00
     scams
    0.93
    Scam
    0.85
     Scam
    0.80
     scammed
    0.78
     fraude
    0.73
     scammers
    0.73
     hoax
    0.72
    ValueStyle
    0.71
     fraud
    0.69
    Activations Density 0.011%

    No Known Activations