© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2183
    Prev
    Next
    INDEX
    Explanations

    references to programming or coding practices related to API methods and data structures

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "box" or related terms

    np_acts-logits-general · gemini-2.0-flash

    box

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     disambiguazione
    -0.54
     désolés
    -0.52
     ActivatedRoute
    -0.52
     ferons
    -0.51
    ensement
    -0.51
     plantar
    -0.50
     asset
    -0.50
    plant
    -0.50
     adipis
    -0.49
     WebDriverWait
    -0.49
    POSITIVE LOGITS
     box
    4.40
     Box
    4.07
    box
    3.97
    Box
    3.87
     BOX
    3.68
     boxes
    3.66
    BOX
    3.53
     Boxes
    3.38
    boxes
    3.29
    Boxes
    3.01
    Activations Density 0.281%

    No Known Activations