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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 13828
    Prev
    Next
    INDEX
    Explanations

    phrases related to death and memorialization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding pronouns or possessives before "death."

    np_acts-logits-general · gemini-2.0-flash

    possessive pronoun followed by death

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.75
     Paglinawan
    -0.69
     continúas
    -0.64
    WriteBarrier
    -0.61
    Насе
    -0.61
    lahraga
    -0.60
     Waray
    -0.60
     تضيفلها
    -0.57
    Rujuakan
    -0.56
    harmed
    -0.54
    POSITIVE LOGITS
     death
    1.31
    death
    1.01
     departure
    0.94
     demise
    0.94
     sudden
    0.93
     untimely
    0.88
     disappearance
    0.86
     premature
    0.85
     arrival
    0.83
     defeat
    0.82
    Activations Density 0.363%

    No Known Activations