© 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. 2515
    Prev
    Next
    INDEX
    Explanations

    specific regional names or locations, particularly in a South Asian context

    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
    rungsseite
    -0.85
    KommentareTeilen
    -0.80
     EconPapers
    -0.76
     nakalista
    -0.72
    NameInMap
    -0.72
     وتسجيلات
    -0.71
     Audiodateien
    -0.71
     Waray
    -0.69
    OOTDTY
    -0.69
    XmlAccessorType
    -0.69
    POSITIVE LOGITS
    çük
    0.63
     Old
    0.61
    Old
    0.60
     小
    0.59
     old
    0.58
     OLD
    0.56
     Little
    0.56
    老
    0.54
    Little
    0.53
    小
    0.52
    Activations Density 1.365%

    No Known Activations