© 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
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 8039
    Prev
    Next
    INDEX
    Explanations

    concepts related to police actions and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.48
    ècie
    -0.44
    carton
    -0.40
     hubieran
    -0.38
     scattata
    -0.36
     increí
    -0.36
    !")
    -0.36
     aparecen
    -0.36
    /*!
    -0.35
     zeichnet
    -0.35
    POSITIVE LOGITS
     POLICE
    0.57
     policemen
    0.56
     Police
    0.56
     policeman
    0.54
    police
    0.54
     ब्रेकडाउन
    0.54
     police
    0.53
    Police
    0.52
    MigrationBuilder
    0.51
     Policing
    0.51
    Activations Density 0.746%

    No Known Activations