© 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. 20-GEMMASCOPE-RES-16K
    11. 8499
    Prev
    Next
    INDEX
    Explanations

    terms associated with criminal activity and legal proceedings

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

    Robbery or theft

    np_acts-logits-general · gemini-2.0-flash

    armed robbery and theft

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    IHC
    -0.49
     Superhost
    -0.49
    ]<<"
    -0.48
     Weiss
    -0.48
     Nagasaki
    -0.48
    UnitTesting
    -0.48
    verso
    -0.48
    ృ
    -0.47
    GraphicsUnit
    -0.46
    setFilter
    -0.46
    POSITIVE LOGITS
     theft
    1.86
     thieves
    1.81
     thief
    1.81
     robbery
    1.79
     stolen
    1.78
     thefts
    1.67
     stealing
    1.65
     steal
    1.63
     Theft
    1.63
    Theft
    1.54
    Activations Density 0.399%

    No Known Activations