© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7714
    Prev
    Next
    INDEX
    Explanations

    references to deceased individuals or the concept of being deceased

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     []:
    -0.36
    nEnter
    -0.35
     montr
    -0.35
    ]->
    -0.34
    IntoConstraints
    -0.34
     diha
    -0.34
    bigsqcup
    -0.32
    ứng
    -0.32
     intégr
    -0.32
     suel
    -0.31
    POSITIVE LOGITS
     deceased
    1.20
     Deceased
    1.13
    deceased
    1.13
     late
    0.98
     verstor
    0.90
     fallecido
    0.89
     dead
    0.88
    late
    0.85
     LATE
    0.84
     zmar
    0.82
    Activations Density 0.167%

    No Known Activations