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. 12454
    Prev
    Next
    INDEX
    Explanations

    issues related to infrastructure and utility services

    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
     models
    -0.28
    vičius
    -0.28
     Abubakar
    -0.28
    usa
    -0.27
     Evidence
    -0.26
    ikum
    -0.26
     Aside
    -0.26
     bò
    -0.26
    list
    -0.25
     model
    -0.25
    POSITIVE LOGITS
     electricity
    0.86
     المعيارى
    0.82
     disambiguazione
    0.80
    EDEFAULT
    0.73
    Electricity
    0.72
    RTDA
    0.71
     electric
    0.71
     ویکی‌پدیا
    0.69
     sumpay
    0.69
     pinulongan
    0.68
    Activations Density 0.190%

    No Known Activations