© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14714
    Prev
    Next
    INDEX
    Explanations

    references to deaths and the circumstances surrounding them

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

    Tokens after a name, potentially indicating death

    np_acts-logits-general · gemini-2.0-flash

    death and dying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    stylers
    -0.42
    tomans
    -0.41
    getFull
    -0.40
    nologue
    -0.40
    ourage
    -0.38
    ovy
    -0.38
     nara
    -0.37
    quiao
    -0.36
    ambique
    -0.36
    تقاوى
    -0.35
    POSITIVE LOGITS
     propOrder
    0.48
     cejas
    0.48
    SharedDtor
    0.48
     كومونز
    0.46
    Handlung
    0.43
    ChildScrollView
    0.42
    RTCF
    0.41
    UpInside
    0.41
    Демографія
    0.40
    GenerationType
    0.39
    Activations Density 0.398%

    No Known Activations