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. 40802
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to object-relational mapping (ORM) concepts in software development

    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
     Pfund
    -0.52
     Italij
    -0.50
    antaranya
    -0.49
     Dichter
    -0.48
     snippetHide
    -0.46
     tận
    -0.45
     delante
    -0.45
     personales
    -0.45
     mêmes
    -0.45
    offsetof
    -0.45
    POSITIVE LOGITS
    jooq
    1.29
    oredCriteria
    0.41
     Seeder
    0.36
     Hover
    0.36
    webElementXpaths
    0.35
     Bound
    0.35
     aqu
    0.34
    CGRectMake
    0.33
    RTLU
    0.33
     Bolt
    0.33
    Activations Density 0.001%

    No Known Activations