© 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. 18-GEMMASCOPE-RES-16K
    11. 436
    Prev
    Next
    INDEX
    Explanations

    phrases related to ethical considerations and implications

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

    "into", "of", or "to" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    taken into consideration or account

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -1.24
     ویکی‌پدیا
    -1.22
    GEBURTSDATUM
    -1.06
    ьаж
    -1.04
     Paglinawan
    -1.02
     pinulongan
    -1.00
     transfieras
    -0.95
    mybatisplus
    -0.95
    InitVars
    -0.94
    脚注の使い方
    -0.93
    POSITIVE LOGITS
    ↵↵↵
    0.59
    <eos>
    0.50
    ​​
    0.45
     Co
    0.45
    ​
    0.44
    '
    0.44
    ‎
    0.44
    ’
    0.43
    ĺ
    0.42
    ADVERTISEMENT
    0.42
    Activations Density 0.588%

    No Known Activations