© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 1007
    Prev
    Next
    INDEX
    Explanations

    elements related to structured processes, methods, and parts involved in systems or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dieux
    -0.61
    yordu
    -0.55
     partenza
    -0.54
     cerâmica
    -0.54
     adopción
    -0.53
     enfans
    -0.52
     vœux
    -0.52
     sœurs
    -0.51
    bitkan
    -0.50
     eventuali
    -0.49
    POSITIVE LOGITS
     оригіналу
    1.22
    ImageContext
    0.98
    protoimpl
    0.86
     متعلقه
    0.84
    IsMutable
    0.83
    NameInMap
    0.81
    ็จ
    0.80
    ruptedException
    0.79
     المعيارى
    0.78
    StructEnd
    0.77
    Activations Density 0.127%

    No Known Activations