© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 16240
    Prev
    Next
    INDEX
    Explanations

    the term "unprecedented" and related expressions highlighting unique or extraordinary situations

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

    unprecedented qualification of intensity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ỏ
    -0.36
    Coil
    -0.34
    Fill
    -0.34
    box
    -0.32
     box
    -0.32
    List
    -0.32
    Line
    -0.32
    Colors
    -0.32
    Lay
    -0.32
     Coil
    -0.31
    POSITIVE LOGITS
     unprecedented
    1.99
    precedented
    1.66
     unparalleled
    1.02
     unusual
    0.93
     extraordinary
    0.88
     unheard
    0.83
     unimaginable
    0.82
     unexpected
    0.82
     unforeseen
    0.82
     inéd
    0.81
    Activations Density 0.003%

    No Known Activations