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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1058
    Prev
    Next
    INDEX
    Explanations

    references to parsing operations and related terminology

    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
     onlyOwner
    -0.73
     StatefulWidget
    -0.72
     superiori
    -0.69
    defineProperty
    -0.69
    帖最后由
    -0.67
    tvguidetime
    -0.66
     &___
    -0.66
     numberWith
    -0.65
    Revenir
    -0.64
    UserScript
    -0.64
    POSITIVE LOGITS
    parse
    2.96
     parse
    2.95
     Parse
    2.72
    Parse
    2.65
     parsing
    2.27
     Parsing
    2.08
     parsed
    2.06
    PARSE
    2.06
    Parsing
    1.92
    parsing
    1.84
    Activations Density 0.059%

    No Known Activations