© 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. 23-GEMMASCOPE-RES-16K
    11. 15404
    Prev
    Next
    INDEX
    Explanations

    words starting with "des" or related to the root "des."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 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
    webElementXpaths
    -0.80
    QMetaType
    -0.63
     stay
    -0.59
     tiết
    -0.59
    mybatisplus
    -0.58
     stayed
    -0.55
    stay
    -0.52
    retung
    -0.52
     flip
    -0.51
     Hitam
    -0.51
    POSITIVE LOGITS
     Des
    0.74
    Des
    0.64
     DES
    0.62
    TagMode
    0.60
     समीक्षक
    0.57
     desp
    0.56
     metast
    0.55
     itſelf
    0.55
     Dez
    0.53
     des
    0.52
    Activations Density 0.126%

    No Known Activations