© 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
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11968
    Prev
    Next
    INDEX
    Explanations

    mentions of fraud and scams, particularly in relation to deceitful practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scribers
    -0.42
    exels
    -0.42
    ssohn
    -0.41
    Statistiche
    -0.38
    thinkable
    -0.38
     arşivlendi
    -0.38
    endid
    -0.37
     affitto
    -0.35
    UnusedPrivate
    -0.35
    twimg
    -0.35
    POSITIVE LOGITS
     scam
    1.88
     fraud
    1.81
     scams
    1.78
     deception
    1.59
     frauds
    1.56
     fraudulent
    1.55
     Fraud
    1.55
     scammers
    1.54
    Fraud
    1.52
    fraud
    1.50
    Activations Density 0.567%

    No Known Activations