© 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. 10593
    Prev
    Next
    INDEX
    Explanations

    phrases and terms associated with specific days and events

    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
    DataAnnotations
    -0.68
     unknownFields
    -0.61
     dàng
    -0.54
    헌
    -0.53
    ódó
    -0.52
     tomba
    -0.51
     étrangers
    -0.51
     AssemblyTitle
    -0.50
     baseman
    -0.50
    ))}
    -0.49
    POSITIVE LOGITS
    تقاوى
    0.57
    celand
    0.56
    SPATH
    0.56
    Ứ
    0.55
    aclk
    0.54
    abetes
    0.52
    setVerticalGroup
    0.52
    llywood
    0.52
    ennifer
    0.52
     itself
    0.51
    Activations Density 1.714%

    No Known Activations