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

    Neuronpedia

    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. 84704
    Prev
    Next
    INDEX
    Explanations

    the word "worse" in various contexts

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

    comparatively worse

    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
     Hallen
    -0.60
    CFA
    -0.59
    digarh
    -0.58
    Abit
    -0.58
    GUID
    -0.57
    phrag
    -0.56
    orianCalendar
    -0.56
    TemporalType
    -0.55
    FID
    -0.54
     Millet
    -0.54
    POSITIVE LOGITS
     worse
    1.92
    worse
    1.86
     Worse
    1.71
    Worse
    1.71
     peores
    1.38
    worst
    1.30
     worst
    1.29
     peor
    1.22
    Worst
    1.20
     Worst
    1.17
    Activations Density 0.006%

    No Known Activations