© 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. 0-GEMMASCOPE-RES-16K
    11. 8282
    Prev
    Next
    INDEX
    Explanations

    references to Germany and its related terms

    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
     Majefty
    -1.14
     Monfieur
    -1.12
    ſelf
    -1.07
     Diſ
    -1.06
     Anſ
    -1.02
     iſt
    -1.01
     Houſe
    -1.00
     estekak
    -1.00
     auffi
    -0.99
     itſelf
    -0.98
    POSITIVE LOGITS
     να
    0.73
     German
    0.60
     
    0.58
     Stu
    0.57
     да
    0.56
    高
    0.54
     Cash
    0.51
     Peter
    0.50
    German
    0.49
     turn
    0.48
    Activations Density 0.096%

    No Known Activations