© 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. 36-GEMMASCOPE-RES-16K
    11. 15972
    Prev
    Next
    INDEX
    Explanations

    references to specific historical figures or accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     traitors
    -0.63
    الدراسه
    -0.62
     elites
    -0.62
     monarchs
    -0.61
     archaeologists
    -0.60
     assholes
    -0.58
     piercings
    -0.58
     witches
    -0.58
     influencers
    -0.57
     ninjas
    -0.57
    POSITIVE LOGITS
    
    0.48
    endregion
    0.37
     للمعارف
    0.35
     gentle
    0.33
     trades
    0.32
     słu
    0.32
     uska
    0.31
     men
    0.31
     wußte
    0.31
    webElement
    0.30
    Activations Density 0.700%

    No Known Activations