© 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. 1-GEMMASCOPE-RES-16K
    11. 13049
    Prev
    Next
    INDEX
    Explanations

    references to capital punishment or the death penalty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [*]
    -0.58
    Chars
    -0.56
    UALA
    -0.54
     ген
    -0.52
    umenical
    -0.50
     IMMEDIATE
    -0.49
    儡
    -0.49
     اساس
    -0.48
    Affiliate
    -0.48
    tungs
    -0.47
    POSITIVE LOGITS
     betweenstory
    0.91
     Efq
    0.88
     death
    0.86
     Death
    0.85
    Death
    0.81
    death
    0.80
    ]--;
    0.71
     Diſ
    0.70
     Inſ
    0.70
     fevere
    0.68
    Activations Density 0.071%

    No Known Activations