© 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
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 8671
    Prev
    Next
    INDEX
    Explanations

    instances of dishonesty, deception, and falsehoods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prudent
    -0.35
    说明
    -0.32
     note
    -0.32
    có
    -0.31
     Kelle
    -0.31
     bruk
    -0.30
     cuch
    -0.30
     plus
    -0.30
     co
    -0.29
     large
    -0.29
    POSITIVE LOGITS
     Fake
    0.88
     mentira
    0.85
     mentiras
    0.84
     falsehood
    0.83
     Deception
    0.82
     deceptive
    0.81
     Fraud
    0.81
     lied
    0.79
     fakes
    0.78
     fake
    0.77
    Activations Density 0.303%

    No Known Activations