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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 7391
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax and function calls related to object and method definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     the
    -0.49
     paix
    -0.36
    òi
    -0.35
     this
    -0.35
    the
    -0.35
    }{*}{}
    -0.35
     wonen
    -0.35
     عنها
    -0.34
     asist
    -0.34
     ceny
    -0.34
    POSITIVE LOGITS
    ьаж
    0.87
    WriteTagHelper
    0.77
     GoogleFonts
    0.77
    ніципалі
    0.75
    tonsoft
    0.66
    HasAnnotation
    0.65
    */].
    0.64
    хьтан
    0.63
     يتيمه
    0.63
     Савезне
    0.63
    Activations Density 0.067%

    No Known Activations