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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 11015
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to law and practice

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

    preceding "practice"

    np_acts-logits-general · gemini-2.0-flash

    veterinary and animal practice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.64
    WaitGroup
    -0.63
    +#+
    -0.62
    WindowConstants
    -0.57
     Muta
    -0.54
     saites
    -0.54
     INTERESAR
    -0.53
     الحره
    -0.53
     المعيارى
    -0.53
    IUrlHelper
    -0.53
    POSITIVE LOGITS
     practice
    3.19
     Practice
    2.85
    practice
    2.79
    Practice
    2.76
     PRACTICE
    2.61
     practicing
    2.35
     practise
    2.31
    PRACTICE
    2.27
     practiced
    2.21
     practices
    2.12
    Activations Density 0.279%

    No Known Activations