© 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. 10-GEMMASCOPE-RES-16K
    11. 15496
    Prev
    Next
    INDEX
    Explanations

    references to brands or products, particularly those starting with "Bo"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gundam
    -0.92
     McP
    -0.92
     gundam
    -0.89
     urea
    -0.84
    ?」
    -0.84
     Reiche
    -0.83
    pernic
    -0.82
     Urea
    -0.82
     Cuar
    -0.82
     McColl
    -0.82
    POSITIVE LOGITS
     Bo
    0.93
    bo
    0.88
     bo
    0.83
    Bo
    0.83
     BO
    0.79
     Sab
    0.76
     Boch
    0.73
     Bog
    0.71
    toolStripButton
    0.70
    積み
    0.68
    Activations Density 0.511%

    No Known Activations