© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 7935
    Prev
    Next
    INDEX
    Explanations

    instances of the word "suffer" and its variations, indicating a focus on experiences of pain or distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lexia
    -0.75
    ContentAsync
    -0.74
    ntk
    -0.74
     numberWith
    -0.73
     Kenney
    -0.73
     Pineda
    -0.72
     Lyn
    -0.71
    cinct
    -0.69
     Webster
    -0.68
     Holt
    -0.67
    POSITIVE LOGITS
     suffer
    1.82
     suffered
    1.78
     Suffer
    1.78
     suffering
    1.75
     suffers
    1.72
    suffering
    1.58
     sufferer
    1.49
     Suffering
    1.48
     sufferings
    1.44
     sufferers
    1.40
    Activations Density 0.049%

    No Known Activations