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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1257
    Prev
    Next
    INDEX
    Explanations

    instances of the word "practice" and related forms in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "practice"

    np_acts-logits-general · gemini-2.0-flash

    practice and practical application

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thschild
    -0.50
     Helmet
    -0.47
     Coulomb
    -0.46
     tidings
    -0.45
    roids
    -0.45
     Crom
    -0.45
     uranium
    -0.44
    heimer
    -0.44
     Bolivar
    -0.44
     Coul
    -0.44
    POSITIVE LOGITS
     practice
    1.08
    practice
    1.08
     Practice
    1.06
     PRACTICE
    1.05
    Practice
    1.05
     practise
    1.04
    PRACTICE
    0.99
    practi
    0.93
    Practi
    0.90
     practices
    0.89
    Activations Density 0.103%

    No Known Activations