© 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. 1-GEMMASCOPE-RES-16K
    11. 7696
    Prev
    Next
    INDEX
    Explanations

    technical jargon and terminology related to particle physics experiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hồng
    -0.40
    liferay
    -0.39
    EditorBrowsable
    -0.37
    hatic
    -0.36
     Fuerzas
    -0.36
    社
    -0.36
     roca
    -0.35
    UIKit
    -0.34
     kym
    -0.34
    MeasureSpec
    -0.34
    POSITIVE LOGITS
    存于互联网档案馆
    0.97
    IntoConstraints
    0.92
     المعيارى
    0.84
    __":
    0.78
    featureID
    0.70
    omeness
    0.68
    ագրություններ
    0.64
    Diwedd
    0.63
    RenderAtEndOf
    0.62
    __':
    0.62
    Activations Density 1.088%

    No Known Activations