© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 10248
    Prev
    Next
    INDEX
    Explanations

    negations and words indicating mathematical functions or operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſind
    -0.79
     שוליים
    -0.69
     InputDecoration
    -0.69
     kasarigan
    -0.68
     témoig
    -0.68
     zuſammen
    -0.68
     ſont
    -0.67
     beſte
    -0.67
    GIH
    -0.66
     dieſer
    -0.65
    POSITIVE LOGITS
    (-
    1.01
     (-
    0.90
    {-
    0.87
    [-
    0.85
     -
    0.84
    =-
    0.83
    −
    0.83
     $-
    0.82
    ,-
    0.79
    ([-
    0.75
    Activations Density 1.343%

    No Known Activations