© 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. 5589
    Prev
    Next
    INDEX
    Explanations

    references to conventions and conventional practices

    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
     hashlib
    -0.81
    ModelSerializer
    -0.79
     cser
    -0.78
    CompleteListener
    -0.76
    HRP
    -0.73
     Melissa
    -0.71
     SPONS
    -0.70
     varmt
    -0.68
     Corcoran
    -0.67
    ikbaar
    -0.67
    POSITIVE LOGITS
    Convention
    1.94
     convention
    1.92
     Convention
    1.82
     Conventions
    1.75
     conventions
    1.75
    convention
    1.72
    Conven
    1.65
     Conventional
    1.62
    Conventional
    1.54
     conventional
    1.48
    Activations Density 0.128%

    No Known Activations