© 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. 21-GEMMASCOPE-RES-16K
    11. 2336
    Prev
    Next
    INDEX
    Explanations

    terms related to JavaScript object property descriptors and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     salvo
    -0.55
     morgue
    -0.50
     Ouv
    -0.49
     gorg
    -0.48
     CommandType
    -0.46
    folium
    -0.45
    ppet
    -0.44
     isSelected
    -0.44
    XtraGrid
    -0.43
     tit
    -0.43
    POSITIVE LOGITS
     nahilalakip
    0.70
    copa
    0.57
    quelize
    0.56
     Prototype
    0.55
     prototype
    0.55
     côtés
    0.54
    SharedCtor
    0.53
    prototype
    0.53
    éez
    0.53
    Prototype
    0.52
    Activations Density 0.406%

    No Known Activations