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-2-9B
    4. Residual Stream - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65783
    Prev
    Next
    INDEX
    Explanations

    punctuation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     many
    -0.44
     StatefulWidget
    -0.40
    /*
    -0.39
     Especially
    -0.38
     especially
    -0.37
     "..\..\..\
    -0.36
     agents
    -0.36
     wiele
    -0.35
    AutoScale
    -0.35
     مُعرِّف
    -0.34
    POSITIVE LOGITS
     essentially
    0.74
    similar
    0.71
    essentially
    0.71
    類似
    0.69
     similar
    0.69
     Essentially
    0.67
    Essentially
    0.66
     Similar
    0.64
    Similar
    0.62
     optionally
    0.62
    Activations Density 0.174%

    No Known Activations