© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13496
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and software development

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

    after technical terms in other languages

    np_acts-logits-general · gemini-2.0-flash

    server, file, page, value

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     argint
    -0.59
    Aggi
    -0.52
     enfans
    -0.52
     cielos
    -0.51
     dată
    -0.50
     cappuccio
    -0.48
     Públicas
    -0.48
     Syrie
    -0.48
    före
    -0.48
     picioare
    -0.47
    POSITIVE LOGITS
    بوابة
    0.82
    Portale
    0.80
    UIControlState
    0.68
    %)$
    0.63
    Portail
    0.62
    ValueStyle
    0.62
    AnchorStyles
    0.60
    featureID
    0.57
    RegressionTest
    0.54
    LEncoder
    0.54
    Activations Density 0.086%

    No Known Activations