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. 69573
    Prev
    Next
    INDEX
    Explanations

    references to various forms and applications, particularly in legal and administrative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    WriteLiteral
    -0.46
     ब्रेकडाउन
    -0.43
     jugement
    -0.40
     pasaje
    -0.37
     gött
    -0.37
     gifting
    -0.35
    Données
    -0.35
     lujo
    -0.34
     EconPapers
    -0.34
     plaisir
    -0.34
    POSITIVE LOGITS
     Form
    0.60
     form
    0.58
     paperwork
    0.58
    ształ
    0.56
     forms
    0.56
     sheet
    0.56
     sheets
    0.54
     leaflet
    0.54
    msgTypes
    0.53
     форме
    0.52
    Activations Density 0.033%

    No Known Activations