© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 7259
    Prev
    Next
    INDEX
    Explanations

    terms associated with law enforcement and illegal activity

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

    law enforcement and crime

    np_acts-logits-general · gemini-2.0-flash

    police officers and arrests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.71
    الحياه
    -0.63
    ArrowToggle
    -0.60
     Thrones
    -0.57
     Donors
    -0.55
    urances
    -0.55
    Vote
    -0.55
     незавершена
    -0.55
    VOTE
    -0.53
     Betis
    -0.53
    POSITIVE LOGITS
     police
    1.02
     cops
    0.85
    police
    0.85
     Police
    0.84
    Police
    0.82
     arrest
    0.81
     officers
    0.79
     enforcement
    0.79
     patrol
    0.78
     POLICE
    0.78
    Activations Density 0.559%

    No Known Activations