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

    Neuronpedia

    Jacobian LensNEW
    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. 11-GEMMASCOPE-RES-16K
    11. 3146
    Prev
    Next
    INDEX
    Explanations

    terms related to crime and criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ILayout
    -0.85
    Personensuche
    -0.80
     Préférences
    -0.72
    LookAnd
    -0.70
     дописавши
    -0.69
     محفوظة
    -0.69
    ASHINGTON
    -0.68
    ressee
    -0.67
    انجليز
    -0.66
    脚注の使い方
    -0.65
    POSITIVE LOGITS
     crime
    1.76
     Crime
    1.69
     crimes
    1.62
     CRIME
    1.54
    Crime
    1.52
     Crimes
    1.45
    crime
    1.41
     crimen
    1.26
     criminal
    1.26
    crimes
    1.21
    Activations Density 0.133%

    No Known Activations