© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9413
    Prev
    Next
    INDEX
    Explanations

    descriptions of medical conditions and procedures, particularly in the context of surgical experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    reconstructions at, values above, greater if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dommages
    -0.67
     démocr
    -0.65
     rigue
    -0.65
     ordinaires
    -0.65
     réfrig
    -0.65
     normaux
    -0.64
     vectorielles
    -0.64
     défis
    -0.64
    seteq
    -0.64
    tagHelperRunner
    -0.63
    POSITIVE LOGITS
     notably
    0.70
     :
    0.65
     :
    0.60
    Compartir
    0.57
     tuto
    0.56
     punctuated
    0.55
     gebeurt
    0.55
    ïa
    0.54
     adapted
    0.53
     Indeed
    0.53
    Activations Density 0.545%

    No Known Activations