© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 108467
    Prev
    Next
    INDEX
    Explanations

    specific programming terminology and concepts related to gesture recognition in user interface development

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

    touches began with event

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    tagHelperRunner
    -1.02
    AddTagHelper
    -0.81
    ſelves
    -0.75
     للمعارف
    -0.71
    TagMode
    -0.69
    expandindo
    -0.68
    PropertyChanging
    -0.68
    Tembelea
    -0.66
    تقاوى
    -0.63
    出版年
    -0.63
    POSITIVE LOGITS
     MotionEvent
    0.29
     circunstancias
    0.29
    msgSender
    0.28
     circunstancia
    0.28
     Bewegung
    0.28
     ocasião
    0.28
     ejes
    0.27
     Stoff
    0.27
     événement
    0.27
     inappropriés
    0.27
    Activations Density 0.010%

    No Known Activations