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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 17-GEMMASCOPE-RES-65K
    6. 28482
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "happen" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ագրություններ
    -0.80
     Normdatei
    -0.75
     Himo
    -0.65
    createCanvas
    -0.65
    utsal
    -0.64
     DHS
    -0.63
    ostok
    -0.62
     Matos
    -0.61
    Autoritní
    -0.61
    EnableWeb
    -0.61
    POSITIVE LOGITS
     HAPP
    1.05
     happen
    0.99
     happened
    0.99
     Happen
    0.98
     happening
    0.96
     happens
    0.96
     Happens
    0.87
     Happened
    0.86
    happen
    0.85
    stance
    0.82
    Activations Density 0.012%

    No Known Activations