© 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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7688
    Prev
    Next
    INDEX
    Explanations

    references to organized crime and law enforcement activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URLException
    -0.52
     dielectric
    -0.50
    كتشاف
    -0.50
    ulemon
    -0.50
    Quinta
    -0.49
    iferous
    -0.48
    readObject
    -0.48
     SwiftUI
    -0.48
    ברס
    -0.47
     canlynol
    -0.47
    POSITIVE LOGITS
     gangster
    1.19
     gang
    1.18
     gangsters
    1.11
     gangs
    1.08
     mafia
    1.08
     underworld
    1.04
     Mafia
    1.02
     drug
    1.02
     crime
    1.02
     criminal
    0.95
    Activations Density 0.501%

    No Known Activations