© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9389
    Prev
    Next
    INDEX
    Explanations

    technical terms and metrics related to computer vision methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }}$}
    -0.65
    ंदीखरीदारी
    -0.60
    Silen
    -0.52
     schade
    -0.50
     Paglinawan
    -0.49
     xenia
    -0.46
    ็จ
    -0.46
    Enclosure
    -0.46
    doPost
    -0.46
    literals
    -0.45
    POSITIVE LOGITS
     ujednoznacz
    0.62
    zwald
    0.54
    witt
    0.53
    opencv
    0.52
     gynhyrchwyd
    0.52
    hog
    0.52
     Italijani
    0.51
    jne
    0.51
    gameserver
    0.51
    LEON
    0.51
    Activations Density 1.132%

    No Known Activations