© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1861
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations, names, and entities

    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
     Cah
    -0.67
     dran
    -0.66
    RectangleBorder
    -0.65
     buty
    -0.65
     kaas
    -0.61
     Saran
    -0.60
     Federer
    -0.60
    keren
    -0.60
     Pemberton
    -0.59
    ंदीखरीदारी
    -0.59
    POSITIVE LOGITS
     Beale
    0.90
    scalatest
    0.80
     Nanjing
    0.77
     Reh
    0.76
    OGND
    0.75
     Gleaner
    0.75
     Paglinawan
    0.72
    roxene
    0.71
     Fife
    0.71
    sety
    0.70
    Activations Density 4.985%

    No Known Activations