© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 9608
    Prev
    Next
    INDEX
    Explanations

    elements or properties related to JSON and its structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Servs, phen, xff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -1.05
    ergic
    -0.74
    #
    -0.72
     AssemblyProduct
    -0.71
    erals
    -0.69
    erate
    -0.67
     שוליים
    -0.67
    Portail
    -0.65
    erol
    -0.65
    ER
    -0.65
    POSITIVE LOGITS
    y
    0.43
    了一种
    0.37
     Warwickshire
    0.37
    𝑖
    0.35
     Utf
    0.35
    的一种
    0.34
    的特点
    0.34
     Bedford
    0.33
    maktadır
    0.33
    损伤
    0.33
    Activations Density 0.214%

    No Known Activations