© 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. 33-GEMMASCOPE-RES-16K
    11. 13512
    Prev
    Next
    INDEX
    Explanations

    variations of the letter 'e' and its context in phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     totiž
    -0.57
     nemlig
    -0.56
     allerdings
    -0.53
     nämlich
    -0.50
     natomiast
    -0.50
     bowiem
    -0.48
     समीक्षक
    -0.48
     Tatsache
    -0.48
    ailleurs
    -0.48
     inoltre
    -0.47
    POSITIVE LOGITS
     Islamic
    0.45
    像
    0.44
     old
    0.44
     говоря
    0.43
    ntilde
    0.43
     gross
    0.43
    埋
    0.43
    :
    0.43
     southwestern
    0.43
     للمعارف
    0.43
    Activations Density 0.232%

    No Known Activations