© 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. 34-GEMMASCOPE-RES-16K
    11. 13441
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty and self-awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     creemos
    -0.39
     qualitatively
    -0.32
     consistently
    -0.32
     peacefully
    -0.31
     acepta
    -0.30
     gustaría
    -0.30
     confiable
    -0.30
     reportedly
    -0.30
     gracia
    -0.29
     meaningfully
    -0.29
    POSITIVE LOGITS
     disambiguazione
    0.80
     cliche
    0.77
     exaggeration
    0.77
     cliché
    0.77
     sounding
    0.77
     spoiler
    0.74
     spoilers
    0.73
     bias
    0.73
     незавершена
    0.72
     kaarangay
    0.69
    Activations Density 0.463%

    No Known Activations