© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15918
    Prev
    Next
    INDEX
    Explanations

    quantitative data about populations and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     оригіналу
    -0.63
    Bakgrunnsstoff
    -0.59
     تضيفلها
    -0.56
    matchCondition
    -0.53
    bkz
    -0.52
     testSet
    -0.52
     Norden
    -0.51
    :✨
    -0.51
    kret
    -0.51
     penetrate
    -0.50
    POSITIVE LOGITS
    人数
    0.72
     enrollment
    0.67
     crowds
    0.66
    исленность
    0.63
     enrolled
    0.62
    apimachinery
    0.61
     počet
    0.56
     occupancy
    0.56
    astify
    0.55
     Enrollment
    0.55
    Activations Density 0.382%

    No Known Activations