Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 6229
    Prev
    Next
    INDEX
    Explanations

    the term "practice" and its variations, indicating a focus on methods or actions within specific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yargs
    -0.73
    ConstraintMaker
    -0.72
    addSubview
    -0.71
     Colman
    -0.70
    InputModule
    -0.65
     Ked
    -0.63
    åd
    -0.63
    més
    -0.63
    ngOnInit
    -0.62
     Cables
    -0.62
    POSITIVE LOGITS
     practice
    3.96
     Practice
    3.65
    Practice
    3.50
    practice
    3.46
     PRACTICE
    3.44
     practise
    3.11
    PRACTICE
    3.06
     practices
    2.95
     practiced
    2.88
     practicing
    2.80
    Activations Density 0.040%

    No Known Activations