© 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. 7245
    Prev
    Next
    INDEX
    Explanations

    terms associated with military applications and patient-related contexts

    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
     betweenstory
    -0.73
     ligiloj
    -0.68
     EconPapers
    -0.62
    RegistryLite
    -0.60
    脚注の使い方
    -0.60
    hyrchwyd
    -0.57
    Personensuche
    -0.57
    
    -0.57
    OGND
    -0.57
    
    -0.55
    POSITIVE LOGITS
     Vorbild
    0.38
    expliquer
    0.36
     Unterricht
    0.35
     Kle
    0.34
    EndContext
    0.32
     Beschluss
    0.32
     summers
    0.32
    ennemi
    0.32
     charbon
    0.31
    Ejec
    0.31
    Activations Density 2.290%

    No Known Activations