Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53531
    Prev
    Next
    INDEX
    Explanations

    instances of the word "weird" and related expressions describing oddity or strangeness

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

    weirdness and oddity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    multicolumn
    -0.73
     Audiodateien
    -0.72
     referenties
    -0.70
    timbangkan
    -0.61
    شرين
    -0.60
    әһ
    -0.60
    cino
    -0.60
     समीक्षक
    -0.59
    chkin
    -0.56
     hectáreas
    -0.55
    POSITIVE LOGITS
     Weird
    0.90
     wierd
    0.87
    izarre
    0.85
     weird
    0.85
     Strange
    0.84
     bizarre
    0.82
     étrange
    0.82
     strange
    0.82
     quirk
    0.79
    Weird
    0.78
    Activations Density 0.034%

    No Known Activations