© 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. 4-GEMMASCOPE-RES-16K
    11. 15300
    Prev
    Next
    INDEX
    Explanations

    expressions of high praise or enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __["
    -0.87
    gantung
    -0.76
    jspx
    -0.75
    nestjs
    -0.73
    NameInMap
    -0.72
    XtraBars
    -0.72
    μει
    -0.71
    jectures
    -0.71
    HomeAsUpEnabled
    -0.71
    ToScroll
    -0.71
    POSITIVE LOGITS
    Awesome
    1.21
     Awesome
    1.17
    awesome
    1.11
     awesome
    1.07
     AWESOME
    0.96
    esomeness
    0.86
    sigma
    0.85
     Woodward
    0.85
     Montoya
    0.82
    orithmic
    0.77
    Activations Density 0.096%

    No Known Activations