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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 111069
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to scams and fraudulent activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scam
    -1.37
     scams
    -1.15
     Scam
    -1.13
    Scam
    -1.09
     scammers
    -0.95
     scammer
    -0.86
     scammed
    -0.71
     Sca
    -0.58
    骗
    -0.56
    Sca
    -0.54
    POSITIVE LOGITS
     tartalomajánló
    0.60
     препратки
    0.59
     HasFactory
    0.57
     EconPapers
    0.54
    ########.
    0.54
    таратура
    0.49
     stanovnika
    0.48
    dough
    0.47
    Vidite
    0.46
    ]++;
    0.43
    Activations Density 0.001%

    No Known Activations