© 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. 31-GEMMASCOPE-RES-16K
    11. 6091
    Prev
    Next
    INDEX
    Explanations

    references to truth and the accuracy of information

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

    phrases that convey honesty, truthfulness, or accurate information being stated or revealed.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.52
    évaluateur
    -0.43
     informée
    -0.42
    SerializedSize
    -0.42
    outSlope
    -0.41
     Reservations
    -0.41
     autorytatywna
    -0.41
    ViewFeatures
    -0.39
     referenties
    -0.39
    setVerticalGroup
    -0.39
    POSITIVE LOGITS
     truth
    2.77
    truth
    2.38
     Truth
    2.23
    Truth
    2.22
     TRUTH
    2.11
     truths
    2.06
     reality
    1.91
     Wahrheit
    1.88
     verità
    1.80
     vérité
    1.74
    Activations Density 0.512%

    No Known Activations