© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 34011
    Prev
    Next
    INDEX
    Explanations

    references to various types of wires and their bonding techniques

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

    wire organizer, transfer, bonding

    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
    jspx
    -0.66
     Infórmanos
    -0.58
     defaultstate
    -0.57
     pomeriggio
    -0.57
     nahilalakip
    -0.56
    /**
    -0.56
    retudo
    -0.54
    ngrx
    -0.54
    逅
    -0.51
    Caz
    -0.51
    POSITIVE LOGITS
     wire
    1.36
     Wire
    1.34
    Wire
    1.32
    wire
    1.27
     wires
    1.11
     Wires
    1.09
     WIRE
    1.08
    WIRE
    0.93
    wires
    0.91
     alambre
    0.88
    Activations Density 0.008%

    No Known Activations