© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 16251
    Prev
    Next
    INDEX
    Explanations

    terms related to direct current (DC) and alternating current (AC) electrical systems and their components

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

    direct current

    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
     increí
    -0.63
     pérd
    -0.62
    niſſe
    -0.58
     vooz
    -0.56
     invokingState
    -0.54
    󠁢
    -0.54
     témoig
    -0.54
     plufieurs
    -0.53
    énario
    -0.52
    iſchen
    -0.52
    POSITIVE LOGITS
     DC
    0.54
     dc
    0.50
     electric
    0.48
     electricity
    0.46
     Dc
    0.43
    aarrggbb
    0.39
     doux
    0.38
    osgi
    0.38
     cha
    0.37
     постоян
    0.36
    Activations Density 0.022%

    No Known Activations