© 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. 11987
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming functions and data structures

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

    Code snippets or programming terms

    np_acts-logits-general · gemini-2.0-flash

    device identifier or timestamp

    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
    </u>
    -0.52
    =[];
    -0.52
    .,
    -0.51
    isis
    -0.49
    ,
    -0.48
     even
    -0.48
    =[]
    -0.48
    </b>
    -0.46
     and
    -0.46
    مه
    -0.46
    POSITIVE LOGITS
    mybatisplus
    0.94
    تقاوى
    0.90
     purpoſe
    0.90
     تضيفلها
    0.85
    AsUp
    0.85
    RegressionTest
    0.84
     utafitiHapana
    0.83
     neceff
    0.83
     ویکی‌پدیای
    0.83
     Roskov
    0.83
    Activations Density 0.137%

    No Known Activations