© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5119
    Prev
    Next
    INDEX
    Explanations

    references to falsehoods, lies, and misleading statements in the context of honesty and integrity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BorderColor
    -0.50
    onha
    -0.49
    жкой
    -0.48
    ngths
    -0.46
    affinity
    -0.46
     uygun
    -0.46
    нибудь
    -0.46
    ırken
    -0.43
    اعمال
    -0.43
     prefer
    -0.43
    POSITIVE LOGITS
     falsehood
    1.07
     liar
    1.03
     perjury
    0.94
     lied
    0.93
     liars
    0.92
    Lies
    0.92
     Lies
    0.88
     untrue
    0.88
     lies
    0.88
     false
    0.88
    Activations Density 0.359%

    No Known Activations