© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 118464
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to deception and dishonesty

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

    deceit, deception, misleading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.54
     Lingkungan
    -0.52
    ldo
    -0.50
     viață
    -0.49
    <tr>
    -0.49
    Willi
    -0.48
     Earle
    -0.48
     Puls
    -0.48
    amil
    -0.48
     Infórmanos
    -0.47
    POSITIVE LOGITS
     Deception
    1.46
     deception
    1.45
     deceptive
    1.35
     deceive
    1.19
     deceiving
    1.15
     deceived
    1.13
     deceit
    1.01
     deceitful
    0.93
     dece
    0.84
     decep
    0.83
    Activations Density 0.012%

    No Known Activations