© 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. 7874
    Prev
    Next
    INDEX
    Explanations

    references to "of" in passages discussing ownership or attribution

    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
    ngrx
    -0.56
     referrerpolicy
    -0.56
    crí
    -0.53
    hoven
    -0.52
     together
    -0.50
    ReusableCell
    -0.50
    ்
    -0.49
     ihop
    -0.49
    ijne
    -0.48
    مصادر
    -0.48
    POSITIVE LOGITS
     Roskov
    0.75
    CardBody
    0.74
     '\\;'
    0.69
     onAnimation
    0.67
    forName
    0.62
    alties
    0.62
    mongoose
    0.59
     spotting
    0.58
    VideoCapture
    0.57
     Triassic
    0.56
    Activations Density 0.296%

    No Known Activations