© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 24807
    Prev
    Next
    INDEX
    Explanations

    dates or numerical information representing significant events or values

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

    years like 2005, 2007, 2009

    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
     للمعارف
    -0.48
     zijne
    -0.38
     revêtement
    -0.37
     CreateTagHelper
    -0.36
     dragón
    -0.36
     Latimer
    -0.36
    ilumin
    -0.35
    BibitemOpen
    -0.35
     Anfitrión
    -0.35
    aptation
    -0.34
    POSITIVE LOGITS
    0
    1.03
    mbggenerated
    0.70
     OFDb
    0.67
     ۲۰۰
    0.59
     Millennium
    0.57
    ../../
    0.56
    StatusOK
    0.56
    ０
    0.56
     AOL
    0.54
     Euro
    0.54
    Activations Density 0.055%

    No Known Activations