© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 128108
    Prev
    Next
    INDEX
    Explanations

    programming or scripting syntax and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    AutoScaleMode
    -0.67
    IUrlHelper
    -0.64
     ویکی‌پدی
    -0.61
    HideFlags
    -0.48
     Wikiseite
    -0.48
    oa̍t
    -0.47
    tangentMode
    -0.47
     Infór
    -0.47
     financiero
    -0.46
     contextes
    -0.45
    POSITIVE LOGITS
    الدراسه
    0.64
     Raff
    0.59
     Kau
    0.54
     pula
    0.52
    OMES
    0.50
     Gil
    0.49
     patron
    0.49
     import
    0.48
     Spr
    0.48
     Tat
    0.48
    Activations Density 0.001%

    No Known Activations