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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15904
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate growth, improvement, or collaborative efforts

    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
    存于互联网档案馆
    -0.47
    bewerken
    -0.47
     Infórmanos
    -0.44
     Jerusalem
    -0.42
     lägen
    -0.42
    icordia
    -0.42
    userRepository
    -0.41
     Museum
    -0.41
     children
    -0.41
     description
    -0.41
    POSITIVE LOGITS
     AssemblyCulture
    0.56
     Aussie
    0.54
    Життєпис
    0.52
    Aussie
    0.52
     aksi
    0.52
    还得
    0.50
    eens
    0.49
     îna
    0.49
    ifty
    0.48
    的实力
    0.48
    Activations Density 0.304%

    No Known Activations