© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 2584
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to programming or data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     XCTest
    -0.83
    __*/
    -0.80
    ---*/
    -0.78
     Xunit
    -0.75
     FormsModule
    -0.73
    ymce
    -0.71
     "..\..\..\
    -0.71
    PerformLayout
    -0.70
    Diwedd
    -0.69
     *__
    -0.67
    POSITIVE LOGITS
    gg
    1.12
    gag
    1.10
    ggg
    1.10
    ag
    1.08
    g
    1.07
    ig
    1.07
    ging
    1.07
     Wag
    1.04
     Cag
    1.03
    ug
    1.02
    Activations Density 2.005%

    No Known Activations