© 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. 9-GEMMASCOPE-RES-131K
    11. 55973
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "arrest" and its variations in legal contexts

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

    arrested on specific dates and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ƚ
    -0.42
    出版年
    -0.38
     تضيفلها
    -0.35
     playing
    -0.35
     powering
    -0.34
    ंदीखरीदारी
    -0.34
     overlay
    -0.33
    COUVER
    -0.33
    complexContent
    -0.32
    migrationBuilder
    -0.32
    POSITIVE LOGITS
     arrest
    1.19
     arrests
    1.16
    Arrest
    1.13
     arrested
    1.09
     Arrest
    1.09
    arrest
    1.05
     Arrested
    0.95
     arresting
    0.89
     detención
    0.86
    逮捕
    0.84
    Activations Density 0.049%

    No Known Activations