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. 12447
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and functionalities related to information processing systems

    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
     Numerade
    -0.67
     nakalista
    -0.50
     AssemblyCulture
    -0.50
     myſelf
    -0.50
     ſont
    -0.49
    ⓧ
    -0.49
     تانيه
    -0.48
    MLLoader
    -0.48
     EconPapers
    -0.48
    veden
    -0.47
    POSITIVE LOGITS
     customer
    0.63
    $_['
    0.56
     CUSTOMER
    0.54
     retail
    0.54
     customers
    0.54
     Retail
    0.54
     Customer
    0.53
    customer
    0.46
    Customer
    0.44
     consumer
    0.44
    Activations Density 0.502%

    No Known Activations