© 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-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 9292
    Prev
    Next
    INDEX
    Explanations

    mentions of a person's legacy and their impact in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vis
    -0.37
     intu
    -0.36
     intuiti
    -0.35
     buffet
    -0.35
     tip
    -0.34
    毒
    -0.34
    ticing
    -0.34
     stress
    -0.34
     telegram
    -0.33
     straight
    -0.33
    POSITIVE LOGITS
     legacy
    1.02
     legado
    0.93
     legacies
    0.92
     posterity
    0.88
     immortality
    0.82
    legacy
    0.80
     reputation
    0.79
     immort
    0.76
     posthum
    0.75
     immortal
    0.74
    Activations Density 0.198%

    No Known Activations