© 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. 30-GEMMASCOPE-RES-16K
    11. 12465
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate deception or manipulation regarding historical narratives or beliefs

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

    Being tricked, fooled, or deceived

    np_acts-logits-general · gemini-2.0-flash

    falling for deception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.46
    usercontent
    -0.43
    httphttps
    -0.41
    ียญ
    -0.38
    MockMvc
    -0.37
     belangrij
    -0.37
    UAGES
    -0.36
    ніципа
    -0.36
     displeasure
    -0.36
    twimg
    -0.36
    POSITIVE LOGITS
     naive
    1.23
     gul
    1.17
     fooled
    1.16
     naïve
    1.11
     naï
    1.05
     unsuspecting
    1.01
     foolish
    0.99
     fool
    0.93
     deceived
    0.91
    naive
    0.90
    Activations Density 0.396%

    No Known Activations