© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5577
    Prev
    Next
    INDEX
    Explanations

    references to terminal structures or assemblies in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Réponses
    -0.81
     otomatig
    -0.73
     فريبيس
    -0.72
    Revenir
    -0.69
     للمعارف
    -0.67
    mybatisplus
    -0.66
    värr
    -0.66
     Öz
    -0.66
     Lainnya
    -0.65
     Fluss
    -0.63
    POSITIVE LOGITS
     terminal
    3.17
     Terminal
    3.01
     terminals
    2.88
    Terminal
    2.88
    terminal
    2.87
     Terminals
    2.68
     TERMIN
    2.22
    termin
    1.92
    TERMIN
    1.91
    Termin
    1.86
    Activations Density 0.083%

    No Known Activations