© 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. 16-GEMMASCOPE-RES-16K
    11. 12758
    Prev
    Next
    INDEX
    Explanations

    negative descriptors related to moral outrage and tragedy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.77
    tagHelperRunner
    -0.66
     الرياضيه
    -0.63
    Personendaten
    -0.61
     vooz
    -0.57
     queſta
    -0.57
     queſto
    -0.57
    <unused43>
    -0.57
     encre
    -0.56
    <unused8>
    -0.56
    POSITIVE LOGITS
     horrifying
    0.87
     horrific
    0.87
     disgusting
    0.81
     horrors
    0.77
     horrible
    0.77
     horror
    0.77
     horrified
    0.74
     appalling
    0.72
     horrendous
    0.70
     hideous
    0.66
    Activations Density 0.187%

    No Known Activations