© 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. 2-GEMMASCOPE-RES-16K
    11. 7754
    Prev
    Next
    INDEX
    Explanations

    references to dragons and related terms within a military or operational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.51
     lathe
    -0.50
    Ventilation
    -0.47
     مشين
    -0.45
    徨
    -0.45
    GEBURTSDATUM
    -0.44
     Ventilation
    -0.42
    
    -0.42
     Durability
    -0.42
     hyö
    -0.41
    POSITIVE LOGITS
    tagHelper
    0.81
    Robinson
    0.69
     Robinson
    0.67
     Saudi
    0.65
     Norse
    0.61
     ROBINSON
    0.60
     Tribal
    0.59
     immerse
    0.59
     immersion
    0.58
    Immer
    0.58
    Activations Density 0.265%

    No Known Activations