© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4793
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals who have passed away

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

    Death, condolences, and mourning

    np_acts-logits-general · gemini-2.0-flash

    death and mourning memorials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quef
    -0.48
     GetEnumerator
    -0.48
    borgs
    -0.46
     kasarigan
    -0.46
     priori
    -0.45
     priming
    -0.45
     prêt
    -0.45
     bored
    -0.45
     prič
    -0.44
     avantaj
    -0.44
    POSITIVE LOGITS
     condolences
    1.51
     obituary
    1.48
     tributes
    1.46
    Tributes
    1.45
     funeral
    1.45
     mourners
    1.43
     mourned
    1.37
     condolence
    1.36
     Condol
    1.34
     posthum
    1.33
    Activations Density 0.174%

    No Known Activations