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. 23-GEMMASCOPE-RES-16K
    6. 12189
    Prev
    Next
    INDEX
    Explanations

    terms related to the detection of fraudulent or scam-like practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.65
     ivelany
    -0.63
     AssemblyTitle
    -0.62
    windowFixed
    -0.60
     AssemblyProduct
    -0.55
    tagHelperRunner
    -0.55
    ilogue
    -0.55
     الرخصة
    -0.54
     veto
    -0.53
    ukone
    -0.53
    POSITIVE LOGITS
     scam
    1.68
     scams
    1.57
     fraud
    1.46
     scammers
    1.45
     scammer
    1.39
     fraudulent
    1.37
     Scam
    1.36
    Scam
    1.33
     scammed
    1.29
    fraud
    1.29
    Activations Density 0.265%

    No Known Activations