© 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. 21-GEMMASCOPE-RES-16K
    11. 12317
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to prevention and risk management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.71
     تقری
    -0.57
    almost
    -0.56
    scryfall
    -0.54
     Almost
    -0.50
    明らかに
    -0.49
    Almost
    -0.49
    CppCodeGen
    -0.49
     almost
    -0.48
    几乎
    -0.47
    POSITIVE LOGITS
     accidentally
    1.09
     inadvertently
    1.03
    万一
    0.90
     inadvert
    0.87
     يتيمه
    0.87
     unintended
    0.86
     accidents
    0.86
     harm
    0.85
    到时候
    0.84
     misunderstand
    0.83
    Activations Density 0.464%

    No Known Activations