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. 120927
    Prev
    Next
    INDEX
    Explanations

    references to progress-related concepts or UI elements

    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
    verwijspagina
    -0.57
    MessageOf
    -0.52
    
    -0.48
     Familien
    -0.42
     ब्रेकडाउन
    -0.41
    KommentareTeilen
    -0.40
     disambiguazione
    -0.40
     الحره
    -0.39
    CodeAnalysis
    -0.38
    Hentet
    -0.37
    POSITIVE LOGITS
     tqdm
    2.34
    WaitGroup
    0.71
    tq
    0.64
     progress
    0.57
     ProgressDialog
    0.56
    progressbar
    0.53
     Iterator
    0.50
    Progress
    0.50
     PROGRESS
    0.50
    ProgressHUD
    0.49
    Activations Density 0.001%

    No Known Activations