© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 8234
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the ability to communicate effectively and build relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.64
     protoimpl
    -0.58
     gyhoeddwyd
    -0.58
    urlpatterns
    -0.57
    scrapy
    -0.56
    bootstrapcdn
    -0.55
     CGRect
    -0.54
    multer
    -0.50
     Coven
    -0.50
    Халык
    -0.50
    POSITIVE LOGITS
     spotting
    0.74
     multi
    0.71
     spot
    0.70
    Spot
    0.68
     Spot
    0.68
    spot
    0.66
     multitasking
    0.62
    multi
    0.61
    MULTI
    0.61
     foresight
    0.61
    Activations Density 0.357%

    No Known Activations