© 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. 0-GEMMASCOPE-RES-16K
    11. 8534
    Prev
    Next
    INDEX
    Explanations

    references to data types and identifiers in programming, particularly focusing on "Long" and "boolean"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nữa
    -0.57
    Personendaten
    -0.57
    ôm
    -0.55
     gynnwys
    -0.55
     spel
    -0.53
     Spel
    -0.53
     simplifié
    -0.52
    وفة
    -0.50
     تكبرها
    -0.50
     design
    -0.50
    POSITIVE LOGITS
     Long
    0.83
     Short
    0.77
    Long
    0.74
    Ready
    0.73
    Short
    0.71
     resourceCulture
    0.70
    mybatisplus
    0.69
    ready
    0.67
    urlpatterns
    0.66
     Ready
    0.64
    Activations Density 0.091%

    No Known Activations