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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 14483
    Prev
    Next
    INDEX
    Explanations

    themes related to revenge and vindictiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.77
     ujednoznacz
    -0.75
     виправивши
    -0.74
    mergeFrom
    -0.62
     surla
    -0.61
    __(/*!
    -0.60
     NSCoder
    -0.56
    ValueStyle
    -0.56
    ModelAdmin
    -0.54
    tableFuture
    -0.54
    POSITIVE LOGITS
     revenge
    0.94
     vengeance
    0.83
     smirked
    0.80
     Revenge
    0.79
     sarcastic
    0.78
     taunt
    0.74
    Revenge
    0.73
     mocking
    0.72
    revenge
    0.72
     vindic
    0.71
    Activations Density 0.248%

    No Known Activations