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. 20-GEMMASCOPE-RES-131K
    6. 117248
    Prev
    Next
    INDEX
    Explanations

    statistical distributions and relevant metrics

    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_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mengak
    -0.44
    锈钢
    -0.38
    AnchorTagHelper
    -0.37
    sen
    -0.35
     Acti
    -0.35
     teach
    -0.35
    Acti
    -0.33
    DataContract
    -0.33
    enst
    -0.33
    eae
    -0.33
    POSITIVE LOGITS
    adaptiveStyles
    0.56
     Autorisations
    0.54
     distributions
    0.51
     &___
    0.49
     gomez
    0.48
     BorderRadius
    0.48
    下载附件
    0.48
     Verteilung
    0.47
    rungsseite
    0.46
    MeasureSpec
    0.46
    Activations Density 0.263%

    No Known Activations