© 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. 14-GEMMASCOPE-RES-16K
    11. 8442
    Prev
    Next
    INDEX
    Explanations

    phrases indicating curiosity and the desire for knowledge or learning more information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recommandons
    -0.54
    prüche
    -0.53
     a
    -0.47
    грамм
    -0.47
    бовал
    -0.45
     end
    -0.43
     imit
    -0.43
    StatusCodes
    -0.43
    原
    -0.42
    ↵
    -0.42
    POSITIVE LOGITS
     about
    1.08
     knowledge
    1.03
    about
    1.02
     knowled
    1.02
    Know
    0.95
     information
    0.94
    knowledge
    0.94
    Inform
    0.93
    enseignements
    0.93
     Know
    0.91
    Activations Density 0.241%

    No Known Activations