© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10164
    Prev
    Next
    INDEX
    Explanations

    terms related to law enforcement and police activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Exemplo
    -0.46
    __*/
    -0.45
    ternut
    -0.44
    Chapitre
    -0.44
     onCreateView
    -0.44
     yym
    -0.43
     riser
    -0.43
     Bundle
    -0.42
     endowment
    -0.40
    binant
    -0.40
    POSITIVE LOGITS
     police
    1.13
     Police
    1.06
     POLICE
    1.05
    Police
    1.00
    police
    1.00
     policemen
    0.85
     policía
    0.85
     policías
    0.79
     polícia
    0.79
     Policía
    0.78
    Activations Density 0.071%

    No Known Activations