© 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. 86236
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or names

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

    ae or AE

    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
    forRoot
    -0.59
    WriteTagHelper
    -0.57
     jScrollPane
    -0.57
     oliver
    -0.56
     InputDecoration
    -0.56
     المعيارى
    -0.53
     виправивши
    -0.52
     inci
    -0.52
    findpost
    -0.51
     propOrder
    -0.50
    POSITIVE LOGITS
    ae
    0.83
    AE
    0.75
     Kae
    0.70
    iae
    0.67
    tae
    0.67
     Mae
    0.63
    Jae
    0.62
     Roe
    0.61
     AE
    0.61
     Gae
    0.60
    Activations Density 0.033%

    No Known Activations