© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 14188
    Prev
    Next
    INDEX
    Explanations

    terms related to government actions and law enforcement activities

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

    before or related to "police"

    np_acts-logits-general · gemini-2.0-flash

    calling police

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     चीज़ों
    -0.64
    jspx
    -0.63
    XmlAccessType
    -0.60
    rungsseite
    -0.58
     BoxFit
    -0.58
     tslint
    -0.56
     AssemblyTitle
    -0.56
    stellungs
    -0.53
     NgModule
    -0.52
    ConstraintMaker
    -0.52
    POSITIVE LOGITS
     police
    1.98
     Police
    1.70
    police
    1.63
    Police
    1.53
     POLICE
    1.42
     policía
    1.24
     Policía
    1.21
     cops
    1.21
     policemen
    1.19
    警察
    1.19
    Activations Density 0.356%

    No Known Activations