© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6609
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions or circumstances involving the term "under."

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

    "under"

    np_acts-logits-general · gemini-2.0-flash

    under specific conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    URLException
    -0.69
     plufieurs
    -0.62
     itſelf
    -0.62
     ainfi
    -0.61
    väg
    -0.60
     fileSize
    -0.54
     păr
    -0.51
     myſelf
    -0.49
     Giappone
    -0.48
     Italij
    -0.48
    POSITIVE LOGITS
     under
    1.38
     Under
    1.31
    under
    1.27
    Under
    1.27
     UNDER
    1.23
    UNDER
    1.08
     unter
    0.95
    neath
    0.88
     beneath
    0.87
     underneath
    0.84
    Activations Density 0.150%

    No Known Activations