© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 62566
    Prev
    Next
    INDEX
    Explanations

    references to police authority and activity

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

    police and law enforcement

    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
    Tikang
    -0.66
    SourceChecksum
    -0.59
    nasium
    -0.57
    tagHelperRunner
    -0.56
    llac
    -0.52
    Chall
    -0.52
    Erreferentziak
    -0.52
    netbeans
    -0.50
    Rebuild
    -0.50
     kasarigan
    -0.49
    POSITIVE LOGITS
     police
    0.46
     Police
    0.41
     Polizei
    0.38
     Policía
    0.38
     criminal
    0.36
     Polres
    0.36
     military
    0.34
     Military
    0.34
     Polsek
    0.34
     law
    0.33
    Activations Density 0.029%

    No Known Activations