© 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-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 868
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to death and loss

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    исленность
    -0.50
     danger
    -0.43
     Danger
    -0.41
     gevaar
    -0.41
     layui
    -0.40
    危險
    -0.38
    danger
    -0.38
     dead
    -0.38
     Dangerous
    -0.37
     Dead
    -0.37
    POSITIVE LOGITS
     tragically
    0.70
     tragic
    0.67
     suicide
    0.63
     preventable
    0.62
     mysteriously
    0.60
     complications
    0.60
    trag
    0.59
     drowned
    0.59
     trag
    0.57
     unnatural
    0.57
    Activations Density 0.472%

    No Known Activations