© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    11. 12846
    Prev
    Next
    INDEX
    Explanations

    discussions about honesty and truthfulness in various contexts

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

    honesty and truth

    np_acts-logits-general · gemini-2.0-flash

    stating the truth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelper
    -0.80
     Paglinawan
    -0.71
    expandindo
    -0.71
    #+#
    -0.70
    Kaynakça
    -0.68
     Италијани
    -0.68
    complexContent
    -0.66
    adaptiveStyles
    -0.62
    :+:
    -0.62
    vscode
    -0.62
    POSITIVE LOGITS
     truth
    2.07
     honesty
    1.95
     honest
    1.89
    truth
    1.79
     truthful
    1.71
    Truth
    1.71
     Truth
    1.69
     TRUTH
    1.67
    honest
    1.60
     truths
    1.54
    Activations Density 0.388%

    No Known Activations