© 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. 11-GEMMASCOPE-RES-16K
    11. 9366
    Prev
    Next
    INDEX
    Explanations

    phrases expressing disbelief or criticism of statements considered false or misleading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 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
     gustaría
    -0.35
    maakt
    -0.32
    ขึ้น
    -0.30
     suspect
    -0.30
     voulais
    -0.29
     pulito
    -0.29
     varmt
    -0.28
     gérer
    -0.28
     écrans
    -0.27
     conferma
    -0.27
    POSITIVE LOGITS
    setVerticalGroup
    0.66
     surla
    0.65
    verwijspagina
    0.59
    ſcher
    0.55
    iculous
    0.55
    latan
    0.54
    iſchen
    0.54
    migrationBuilder
    0.54
    ſchen
    0.53
    ikusbot
    0.53
    Activations Density 0.979%

    No Known Activations