© 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. 27-GEMMASCOPE-RES-16K
    11. 9337
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming errors and code execution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Krist
    -0.35
    ļas
    -0.32
     documentation
    -0.31
     specifik
    -0.31
     suspendu
    -0.29
     klar
    -0.29
      
    -0.29
    instantiate
    -0.28
     Weiden
    -0.28
     lī
    -0.28
    POSITIVE LOGITS
     للاسماء
    0.85
     surla
    0.77
     unknownFields
    0.66
     ddelweddau
    0.66
     JpaRepository
    0.66
    uxxxx
    0.66
     jadx
    0.66
    曖昧さ回避
    0.65
    addContainerGap
    0.65
     isInitialized
    0.65
    Activations Density 0.023%

    No Known Activations