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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3421
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting elements typically found in news articles

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    msgTypes
    -0.36
    dicionado
    -0.36
    évalu
    -0.35
     تضيفلها
    -0.35
    ském
    -0.35
    ereich
    -0.35
    لينكات
    -0.35
    ̸
    -0.35
     transfé
    -0.34
    xhttp
    -0.33
    POSITIVE LOGITS
    KommentareTeilen
    0.58
     IBOutlet
    0.52
    
    
    0.48
     propOrder
    0.47
     nonUne
    0.46
     SqlParameter
    0.46
     initComponents
    0.45
    IBOutlet
    0.45
    NUMX
    0.44
     rodríguez
    0.44
    Activations Density 0.139%

    No Known Activations