© 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. 41-GEMMASCOPE-RES-16K
    11. 5564
    Prev
    Next
    INDEX
    Explanations

    Cyrillic characters and their combinations, indicating a focus on Slavic language content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lise
    -0.61
    intégr
    -0.60
    stor
    -0.57
     internationaux
    -0.56
     officiels
    -0.55
    ky
    -0.54
    va
    -0.53
    nik
    -0.53
    lig
    -0.53
    ved
    -0.52
    POSITIVE LOGITS
     $_"
    0.45
    ей
    0.38
     المعيارى
    0.37
     Plenum
    0.36
     rela
    0.35
     absorb
    0.35
    ен
    0.35
    он
    0.34
    ит
    0.33
    ань
    0.33
    Activations Density 0.012%

    No Known Activations