© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 566
    Prev
    Next
    INDEX
    Explanations

    instances of the word "happen" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     számára
    -0.72
     alá
    -0.71
     zufolge
    -0.70
     Heine
    -0.68
     Malte
    -0.67
     Matos
    -0.66
    pertory
    -0.63
     fortfarande
    -0.63
     Djibouti
    -0.61
    seteq
    -0.61
    POSITIVE LOGITS
     happening
    1.56
     happen
    1.54
     happened
    1.51
     happens
    1.47
     Happen
    1.45
     HAPP
    1.43
    happen
    1.42
     Happens
    1.35
     Happening
    1.35
    happened
    1.31
    Activations Density 0.088%

    No Known Activations