Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9232
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to death or dying, particularly the word "death" itself.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    references to death and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    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
    -0.90
    adpleegd
    -0.84
     ComVisible
    -0.84
    AutoresizingMask
    -0.76
     AVA
    -0.76
     سكانية
    -0.72
     Préférences
    -0.72
    AddTagHelper
    -0.71
    IsContent
    -0.70
    ècie
    -0.69
    POSITIVE LOGITS
     śmier
    0.68
     DEATH
    0.65
     penalty
    0.61
     death
    0.60
    DEATH
    0.59
     toll
    0.59
    Death
    0.58
     Death
    0.57
    💀
    0.57
    bed
    0.56
    Activations Density 0.107%

    No Known Activations