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. 114849
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations

    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
    SBATCH
    -0.43
    keyColumn
    -0.43
    LookAnd
    -0.36
     tails
    -0.35
    stateMutability
    -0.34
     MessageBoxIcon
    -0.34
     Jove
    -0.34
     refs
    -0.34
     betweenstory
    -0.34
     Connexion
    -0.33
    POSITIVE LOGITS
     ditambah
    0.54
    Хьажоргаш
    0.54
     sum
    0.52
     بيها
    0.52
    SequentialGroup
    0.51
    WithIOException
    0.49
     multiplied
    0.48
     RouterModule
    0.48
     subtracted
    0.47
    autoreleasepool
    0.47
    Activations Density 0.594%

    No Known Activations