© 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. 3-GEMMASCOPE-RES-16K
    11. 15480
    Prev
    Next
    INDEX
    Explanations

    elements related to confirmation messages and user actions on accounts

    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
    QMetaType
    -0.81
     AssemblyCulture
    -0.80
    Démographie
    -0.77
     snippetHide
    -0.76
    OGND
    -0.75
    NameInMap
    -0.74
     Efq
    -0.74
     nahilalakip
    -0.73
    ImageContext
    -0.72
    RTEE
    -0.69
    POSITIVE LOGITS
     تس
    0.74
     ανα
    0.74
     пере
    0.70
     pengh
    0.70
    引き
    0.68
    Рас
    0.66
     Ανα
    0.65
    提
    0.65
     peny
    0.64
     مت
    0.64
    Activations Density 0.437%

    No Known Activations