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

    Neuronpedia

    Jacobian LensNEW
    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. 34-GEMMASCOPE-RES-16K
    11. 1372
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting fear of negative consequences or corruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hampir
    -0.66
     quase
    -0.64
    apparently
    -0.63
     aparentemente
    -0.63
     apparently
    -0.60
     supuestamente
    -0.60
     schein
    -0.60
     Almost
    -0.57
     almost
    -0.57
     nästan
    -0.57
    POSITIVE LOGITS
     disaster
    0.74
     catastrophe
    0.71
     disastrous
    0.65
     someday
    0.65
     ruin
    0.64
     collapse
    0.61
     harm
    0.59
     worse
    0.59
     repris
    0.59
     doom
    0.58
    Activations Density 0.732%

    No Known Activations