© 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
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 3041
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to assisted and unassisted suicide

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.38
     alambre
    -0.35
     trouble
    -0.34
     mechanical
    -0.32
     characters
    -0.32
     revêtement
    -0.32
    ICALLY
    -0.32
     accounting
    -0.32
     nar
    -0.32
     sections
    -0.32
    POSITIVE LOGITS
     الرياضيه
    0.73
     nahilalakip
    0.65
    webElementXpaths
    0.64
     Roskov
    0.63
    GTCX
    0.63
    jsxFileName
    0.60
     мәкал
    0.60
     GenerationType
    0.59
     للمعارف
    0.59
    таратура
    0.58
    Activations Density 0.219%

    No Known Activations