© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 10744
    Prev
    Next
    INDEX
    Explanations

    references to crimes, specifically those involving tax evasion and imprisonment

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

    prison or being arrested

    np_acts-logits-general · gemini-2.0-flash

    arrest and jail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.42
    SourceChecksum
    -0.42
     oprot
    -0.40
     Leistungen
    -0.35
    BeginContext
    -0.33
    awtextra
    -0.33
     muertes
    -0.33
     voed
    -0.32
     незавершена
    -0.32
     sukienka
    -0.31
    POSITIVE LOGITS
     arrest
    0.95
     arrested
    0.95
    Arrest
    0.95
     imprisonment
    0.93
     arrests
    0.93
     jailed
    0.91
     Arrest
    0.91
     jail
    0.88
     Arrested
    0.86
    arrest
    0.85
    Activations Density 0.508%

    No Known Activations