© 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. 3-GEMMASCOPE-RES-16K
    11. 304
    Prev
    Next
    INDEX
    Explanations

    statements and claims that assert truthfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.78
    Activités
    -0.70
     AssemblyCompany
    -0.69
     Bernadette
    -0.68
     يتيمه
    -0.68
    laş
    -0.67
     Tampoco
    -0.65
     intermittently
    -0.64
    IndentedString
    -0.64
     Cyclops
    -0.63
    POSITIVE LOGITS
     true
    3.13
     True
    2.73
    true
    2.60
    True
    2.54
     TRUE
    2.53
    TRUE
    2.19
     truer
    1.94
     vrai
    1.83
     verdadero
    1.75
     truest
    1.72
    Activations Density 0.073%

    No Known Activations