© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 58126
    Prev
    Next
    INDEX
    Explanations

    terms related to death and capital punishment

    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
    ništ
    -0.83
    cheme
    -0.77
     ]
    
    -0.72
     Thesaurus
    -0.72
    useppe
    -0.72
    tometer
    -0.71
     nonatomic
    -0.71
     wireType
    -0.70
     Cym
    -0.70
     Пусть
    -0.70
    POSITIVE LOGITS
     DEATH
    1.38
     death
    1.38
     Death
    1.33
    DEATH
    1.31
    Death
    1.22
    death
    1.21
     deaths
    1.20
     Deaths
    1.13
     Muerte
    0.99
     śmier
    0.97
    Activations Density 0.019%

    No Known Activations