© 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. 5432
    Prev
    Next
    INDEX
    Explanations

    the term "Great" in various contexts

    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
     كومونز
    -0.91
    ViewFeatures
    -0.85
    EndContext
    -0.82
    Хьажоргаш
    -0.80
     &___
    -0.78
     Bioaccumulative
    -0.77
     Roskov
    -0.75
    TestingModule
    -0.74
    PMailer
    -0.72
    quelize
    -0.72
    POSITIVE LOGITS
     Great
    2.48
    Great
    2.18
    GREAT
    1.41
     GREAT
    1.17
     Вели
    1.02
     Nice
    1.01
     Good
    0.97
     Großen
    0.90
    Nice
    0.88
    Good
    0.87
    Activations Density 0.095%

    No Known Activations