© 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. 17-GEMMASCOPE-RES-16K
    11. 1595
    Prev
    Next
    INDEX
    Explanations

    statements about truthfulness or dishonesty in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.61
    ≦)
    -0.58
     TextAppearance
    -0.57
     espar
    -0.55
    '))
    -0.51
     RIS
    -0.51
     gaun
    -0.50
    httphttps
    -0.49
     JAXBElement
    -0.49
    poon
    -0.49
    POSITIVE LOGITS
     things
    1.11
     something
    1.03
     thing
    0.98
    Things
    0.89
     THINGS
    0.89
     Things
    0.87
    things
    0.87
    thing
    0.86
     cosas
    0.85
     anything
    0.83
    Activations Density 0.256%

    No Known Activations