© 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. 11283
    Prev
    Next
    INDEX
    Explanations

    mentions of legal warrants

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

    legal warrants

    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
    ifun
    -0.50
     Leipzig
    -0.48
     Fio
    -0.47
     Fei
    -0.46
     Fiji
    -0.45
     FIG
    -0.45
     CBC
    -0.45
    DIS
    -0.45
    ei
    -0.44
    frozen
    -0.44
    POSITIVE LOGITS
     Warrant
    1.05
     warrant
    1.01
    warrant
    1.00
     WARRANT
    0.91
     warrants
    0.78
    arrant
    0.74
     warranted
    0.73
     warran
    0.72
    WARR
    0.72
    warran
    0.68
    Activations Density 0.005%

    No Known Activations