© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3760
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to arrests and legal charges

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

    Follows the word "arrested"

    np_acts-logits-general · gemini-2.0-flash

    arrested for

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     opacity
    -0.42
     Eden
    -0.39
     صف
    -0.39
    cipy
    -0.39
    Fon
    -0.39
     صفحۀ
    -0.38
     boho
    -0.37
    farlane
    -0.37
    Ori
    -0.37
    Nature
    -0.37
    POSITIVE LOGITS
     arrest
    1.08
     arrests
    1.03
     Arrest
    1.00
     arrested
    0.97
    arrest
    0.96
    Arrest
    0.94
     Arrested
    0.80
     arresting
    0.78
     detención
    0.68
    逮捕
    0.66
    Activations Density 0.175%

    No Known Activations