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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6654
    Prev
    Next
    INDEX
    Explanations

    numerical patterns and sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.88
    UserScript
    -0.82
     noDo
    -0.76
    TagMode
    -0.74
     surla
    -0.73
    
    -0.71
    はじめに
    -0.70
    تقاوى
    -0.70
    CloseOperation
    -0.67
     resourceCulture
    -0.65
    POSITIVE LOGITS
     adicionales
    0.52
     táctil
    0.48
     adicionais
    0.47
     Viana
    0.43
     halbe
    0.43
     required
    0.43
     recargable
    0.43
     Ergänzung
    0.43
     hetzelfde
    0.43
     Strecke
    0.42
    Activations Density 1.371%

    No Known Activations