© 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. 20-GEMMASCOPE-RES-16K
    11. 311
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographic locations, especially in Vietnam

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Vietnamese or Chinese place names

    np_acts-logits-general · gemini-2.0-flash

    Vietnamese place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fubject
    -0.75
     ejus
    -0.63
     pleaſure
    -0.62
     quæ
    -0.61
     neceff
    -0.59
     cristian
    -0.58
     Jérusalem
    -0.57
     Monfieur
    -0.57
     pleaf
    -0.56
     caufe
    -0.56
    POSITIVE LOGITS
    StoryboardSegue
    0.93
     bezeichneter
    0.90
     Infórmanos
    0.85
    #+#
    0.82
    ReusableCell
    0.79
    principalColumn
    0.79
    +#+#
    0.77
     autorytatywna
    0.76
    aarrggbb
    0.73
     EconPapers
    0.73
    Activations Density 0.014%

    No Known Activations