© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 9328
    Prev
    Next
    INDEX
    Explanations

    references to architecture and architectural terms

    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
    casus
    -0.69
     HSV
    -0.67
     argint
    -0.64
     Cass
    -0.64
    Vend
    -0.63
    íso
    -0.63
    Record
    -0.63
     Evang
    -0.62
     Horv
    -0.61
     Guilford
    -0.61
    POSITIVE LOGITS
     architecture
    1.74
     Architecture
    1.69
    Architecture
    1.64
     ARCHITECTURE
    1.64
    architecture
    1.61
     architectures
    1.60
    architect
    1.43
    ARCHITECTURE
    1.42
     architectural
    1.40
     arquitectura
    1.30
    Activations Density 0.075%

    No Known Activations