© 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. 5-GEMMASCOPE-RES-16K
    6. 6646
    Prev
    Next
    INDEX
    Explanations

    references to discipline and its applications in various contexts

    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
     veneta
    -0.78
     Rosie
    -0.76
     Cleopatra
    -0.75
     tomatoes
    -0.75
     estimés
    -0.74
    orescent
    -0.73
     treas
    -0.73
     tomato
    -0.73
    HomeAsUpEnabled
    -0.72
     calendriers
    -0.72
    POSITIVE LOGITS
     discipline
    2.41
     Discipline
    2.27
     disciplines
    2.18
    discipline
    2.13
    Discipline
    2.08
     DISCIP
    1.93
    discipl
    1.92
     Discipl
    1.91
     discipl
    1.87
     disciplina
    1.84
    Activations Density 0.115%

    No Known Activations