© 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. 27-GEMMASCOPE-RES-16K
    11. 12096
    Prev
    Next
    INDEX
    Explanations

    text that expresses uncertainty or self-reflection on personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/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.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quoi
    -0.35
     conferencias
    -0.33
     mäng
    -0.31
     tvá
    -0.29
    ówczas
    -0.29
     entrevistas
    -0.28
     locura
    -0.28
    UnusedPrivate
    -0.27
     reuniones
    -0.27
     práce
    -0.26
    POSITIVE LOGITS
     estekak
    0.87
     disambiguazione
    0.86
    AndEndTag
    0.76
    addCriterion
    0.75
     Infórmanos
    0.74
     ویکی‌پدی
    0.73
    elemField
    0.71
    tonode
    0.71
    Архівовано
    0.70
    Rujuakan
    0.69
    Activations Density 0.436%

    No Known Activations