© 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. 2030
    Prev
    Next
    INDEX
    Explanations

    references to scientific articles and their attributes such as titles, authors, and publication details

    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
     femei
    -0.35
     maș
    -0.33
     culoare
    -0.33
     calitate
    -0.33
     lavoratori
    -0.32
    طلحات
    -0.32
     urmă
    -0.30
     oamen
    -0.30
     argint
    -0.29
     Tweede
    -0.29
    POSITIVE LOGITS
     AssemblyCompany
    0.80
     surla
    0.77
    archiviato
    0.73
     المعيارى
    0.71
    mybatisplus
    0.69
    AndEndTag
    0.69
     Numerade
    0.68
    expandindo
    0.63
    GenerationType
    0.62
     يتيمه
    0.60
    Activations Density 4.077%

    No Known Activations