© 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. 10-GEMMASCOPE-RES-16K
    11. 7318
    Prev
    Next
    INDEX
    Explanations

    references to missing persons and related investigative details

    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
    WebVitals
    -0.38
    hyrchwyd
    -0.37
     بيها
    -0.37
     AssemblyCulture
    -0.35
    óticas
    -0.35
     Bav
    -0.33
     înc
    -0.33
    InjectAttribute
    -0.32
     CRT
    -0.31
    ContentLoaded
    -0.31
    POSITIVE LOGITS
     murder
    0.73
     murdered
    0.71
    rungsseite
    0.71
    Murder
    0.70
     Murder
    0.68
     homicide
    0.68
     Homicide
    0.68
    murder
    0.62
     murders
    0.61
     tragically
    0.60
    Activations Density 0.519%

    No Known Activations