© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 4889
    Prev
    Next
    INDEX
    Explanations

    terms related to emotional pain or suffering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leighton
    -0.81
    httphttps
    -0.75
    ALES
    -0.69
     Baran
    -0.69
    vodu
    -0.68
     Coliseum
    -0.67
    agens
    -0.66
    SuppressLint
    -0.66
     Alejandro
    -0.66
     pre
    -0.63
    POSITIVE LOGITS
     hurt
    1.65
     Hurt
    1.61
    hurt
    1.55
    Hurt
    1.48
     hurts
    1.44
     Hurts
    1.35
     hurting
    1.25
     HUR
    1.03
     hurtful
    1.02
    PerformLayout
    0.95
    Activations Density 0.005%

    No Known Activations