© 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. 15-GEMMASCOPE-RES-16K
    11. 1932
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and conjunctions in the context of comparative studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.52
     ModelRenderer
    -0.48
     pono
    -0.46
    orianCalendar
    -0.45
    
    -0.44
    XtraBars
    -0.44
    FXMLLoader
    -0.42
     useAppContext
    -0.42
    adaptiveStyles
    -0.42
    ISupport
    -0.42
    POSITIVE LOGITS
     sebaliknya
    0.42
     AppCompatTheme
    0.42
     Audiodateien
    0.39
     препратки
    0.39
     Exacts
    0.34
     dolayı
    0.33
    grafa
    0.33
     Artículos
    0.33
    technical
    0.33
    pexpr
    0.32
    Activations Density 1.512%

    No Known Activations