© 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. 125726
    Prev
    Next
    INDEX
    Explanations

    references to assembly and disassembly processes

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

    reassembling or putting back together

    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
     regional
    -0.37
    <thead>
    -0.36
    parsedMessage
    -0.35
    此刻
    -0.34
     hjär
    -0.33
     Lak
    -0.32
    ViewChild
    -0.32
    bitField
    -0.32
     moment
    -0.31
    frei
    -0.31
    POSITIVE LOGITS
     reinstalled
    0.60
     reinstall
    0.57
     reinstalling
    0.56
    MessageTagHelper
    0.52
     GenerationType
    0.49
    rebuild
    0.49
     reinstated
    0.48
    󠁴
    0.48
     reinstatement
    0.48
    RenderAtEndOf
    0.48
    Activations Density 0.013%

    No Known Activations