© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 8743
    Prev
    Next
    INDEX
    Explanations

    references to common weakness enumerations (CWEs) and related terms in programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     benefit
    -0.31
    Suppl
    -0.28
     result
    -0.28
     Umgebung
    -0.28
     balance
    -0.27
     balancing
    -0.27
    Плюсы
    -0.26
     passing
    -0.26
     conto
    -0.26
     معمول
    -0.25
    POSITIVE LOGITS
    :✨
    10.06
     EconPapers
    1.39
     autorytatywna
    1.32
    ✨:
    1.28
    SharedCtor
    1.20
    GEBURTSDATUM
    1.20
     nahilalakip
    1.13
    msgTypes
    1.13
    Rüyada
    1.09
    Personendaten
    1.06
    Activations Density 0.003%

    No Known Activations