© 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. 2-GEMMASCOPE-RES-16K
    11. 557
    Prev
    Next
    INDEX
    Explanations

    characters or symbols, particularly kanji or similar characters in different languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -1.49
     myſelf
    -1.32
     himſelf
    -1.32
     Houſe
    -1.22
     themſelves
    -1.22
     Monfieur
    -1.21
     itſelf
    -1.19
     ainfi
    -1.15
    +:+
    -1.13
     beginnetje
    -1.12
    POSITIVE LOGITS
     א
    1.17
     ס
    1.07
     ק
    1.07
     ח
    1.05
     अ
    1.01
     פ
    0.98
     أ
    0.98
     ا
    0.97
     الأ
    0.96
     ال
    0.95
    Activations Density 0.022%

    No Known Activations