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. 14334
    Prev
    Next
    INDEX
    Explanations

    syntax elements and structure in programming code

    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
     resourceCulture
    -0.84
     arşivlendi
    -0.77
     kasarigan
    -0.73
    URLException
    -0.71
    ]")]
    -0.68
    niſſe
    -0.68
     EconPapers
    -0.67
     estekak
    -0.67
    rungsseite
    -0.66
    脚注の使い方
    -0.66
    POSITIVE LOGITS
     class
    0.34
     Class
    0.33
    class
    0.33
     EMER
    0.30
    Emerging
    0.30
    <eos>
    0.29
     Emerging
    0.28
     mé
    0.28
     Desenvolvimento
    0.28
    Develop
    0.28
    Activations Density 0.198%

    No Known Activations