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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 14300
    Prev
    Next
    INDEX
    Explanations

    the concept of learning and its associated processes

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

    educational learning and objectives

    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
    
    -0.62
    VYMaps
    -0.56
    __::
    -0.55
     propOrder
    -0.54
     виправивши
    -0.54
    RRect
    -0.54
     jspb
    -0.52
     يتيمه
    -0.51
    '}}>
    -0.50
     <>",
    -0.50
    POSITIVE LOGITS
     learning
    0.94
    Learning
    0.94
    learning
    0.94
     Learning
    0.91
     aprendizaje
    0.86
     LEARNING
    0.86
    Learner
    0.79
     aprendizagem
    0.79
    LEARNING
    0.77
    learn
    0.71
    Activations Density 0.014%

    No Known Activations