© 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. 9724
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals and entities

    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
     utr
    -0.82
    MethodManager
    -0.81
     nahilalakip
    -0.80
     lenker
    -0.78
     Guter
    -0.76
    jooq
    -0.75
    mtrl
    -0.75
    ovas
    -0.73
    CharStream
    -0.72
     Hof
    -0.71
    POSITIVE LOGITS
     éc
    0.88
    Felix
    0.78
     Heuer
    0.78
     Whipple
    0.77
     Felix
    0.75
     calcite
    0.72
     Gaj
    0.72
     Zit
    0.71
     Energi
    0.71
     Marlin
    0.71
    Activations Density 1.585%

    No Known Activations