© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 12699
    Prev
    Next
    INDEX
    Explanations

    coding-related terms and functions used in a content management system

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

    File paths in Drupal websites

    np_acts-logits-general · gemini-2.0-flash

    Drupal views and taxonomy

    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
     onAnimation
    -0.61
     Valorant
    -0.58
    GenerationType
    -0.58
    PositiveButton
    -0.54
     whatsapp
    -0.50
    InstrumentedTest
    -0.50
     HONORABLE
    -0.50
    writeField
    -0.49
     Apostle
    -0.49
    IATA
    -0.49
    POSITIVE LOGITS
     taxonomy
    0.62
     Drupal
    0.61
    ctools
    0.61
     Sakai
    0.58
     &___
    0.58
     dru
    0.57
    limsy
    0.56
     facie
    0.54
    Drupal
    0.54
     Taxonomy
    0.54
    Activations Density 0.441%

    No Known Activations