© 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. 2-GEMMASCOPE-RES-16K
    11. 7479
    Prev
    Next
    INDEX
    Explanations

    negative emotional descriptors and terms related to suffering or distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saites
    -0.53
    ffindor
    -0.51
     بيها
    -0.51
     onCreateView
    -0.48
     playfully
    -0.48
     Dreaming
    -0.48
    Sunlight
    -0.46
     leisurely
    -0.46
     excitedly
    -0.45
    WireFormatLite
    -0.45
    POSITIVE LOGITS
     horrible
    1.87
     nasty
    1.77
     horrid
    1.64
     awful
    1.61
     terrible
    1.58
     worst
    1.56
     dreadful
    1.53
    worst
    1.48
     ugly
    1.47
    Horrible
    1.47
    Activations Density 0.291%

    No Known Activations