© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3328
    Prev
    Next
    INDEX
    Explanations

    references to crime and punishment, particularly focusing on capturing criminals and consequences for their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.57
     propOrder
    -0.54
    RegistryLite
    -0.50
    UrlResolution
    -0.49
    gráfica
    -0.49
    ssohn
    -0.48
     חיצוניים
    -0.47
    kloped
    -0.47
     Geraadpleegd
    -0.47
     برانيه
    -0.47
    POSITIVE LOGITS
     accountable
    0.76
     guilty
    0.73
     accountability
    0.72
     punished
    0.71
     responsible
    0.62
     punishment
    0.60
     Accountability
    0.57
     punishable
    0.57
     Guilty
    0.56
     guilt
    0.56
    Activations Density 0.380%

    No Known Activations