© 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. 0-GEMMASCOPE-RES-16K
    11. 7190
    Prev
    Next
    INDEX
    Explanations

    references to specific characters in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nav
    -0.33
     Decker
    -0.31
     מט
    -0.30
     Henson
    -0.30
     alt
    -0.30
    Core
    -0.30
     Helens
    -0.30
    ्ड
    -0.29
                            
    -0.29
     compétences
    -0.29
    POSITIVE LOGITS
    tagHelperRunner
    1.07
     فريبيس
    0.78
    sizeCache
    0.73
     nahilalakip
    0.71
     الحره
    0.69
    AddTagHelper
    0.69
    хьтан
    0.68
    EndContext
    0.67
    messageInfo
    0.66
    NUMX
    0.66
    Activations Density 1.768%

    No Known Activations