© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 10907
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lie" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astéro
    -0.58
    UrlResolution
    -0.50
     Lokales
    -0.49
    PhysRevD
    -0.46
     ويكيميديا
    -0.45
    AppMethodBeat
    -0.41
    يميديا
    -0.40
    Gön
    -0.40
     webdriver
    -0.40
     snippetHide
    -0.39
    POSITIVE LOGITS
     lie
    1.83
     lying
    1.47
     Lie
    1.43
    Lie
    1.38
     lay
    1.38
     LAY
    1.36
     LIE
    1.35
     lies
    1.31
    lie
    1.30
     layer
    1.29
    Activations Density 0.185%

    No Known Activations