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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 5650
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements and logical operators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.71
     насељу
    -0.68
     lenker
    -0.64
    makeConstraints
    -0.62
     betweenstory
    -0.59
    __':
    -0.58
    itinéraire
    -0.57
    __":
    -0.56
     disponibilités
    -0.56
    PageFactory
    -0.53
    POSITIVE LOGITS
    ToCheck
    0.71
     checking
    0.68
     check
    0.64
     Checking
    0.64
     análise
    0.63
    检查
    0.62
    檢查
    0.61
     Checks
    0.60
     判断
    0.60
     viewType
    0.60
    Activations Density 0.205%

    No Known Activations