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. 103193
    Prev
    Next
    INDEX
    Explanations

    code block terminators and punctuation in a programming context

    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
    transQ
    -0.86
     مرئيه
    -0.71
    ſcher
    -0.69
    /**
    -0.66
    ValueStyle
    -0.66
    ſelben
    -0.65
     Waſſer
    -0.60
    <unused76>
    -0.60
     ſelb
    -0.60
    <unused7>
    -0.60
    POSITIVE LOGITS
    initComponents
    0.32
    DataBind
    0.31
    adpleegd
    0.29
    Aholisi
    0.27
     prič
    0.25
     Makanan
    0.25
     Sebuah
    0.24
     Савезне
    0.24
    IBOutlet
    0.24
    ReadByte
    0.24
    Activations Density 0.006%

    No Known Activations