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. 23-GEMMASCOPE-RES-131K
    6. 102
    Prev
    Next
    INDEX
    Explanations

    instances of the word "add" and related variations in code

    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_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.80
    transQ
    -0.72
    HasIndex
    -0.61
     ब्रेकडाउन
    -0.60
    ########.
    -0.59
     jScrollPane
    -0.56
    tonode
    -0.56
     Administrativna
    -0.55
    ftagPool
    -0.54
     AssemblyCompany
    -0.54
    POSITIVE LOGITS
    Autoritní
    0.56
    awtextra
    0.45
    BagConstraints
    0.43
    contentLoaded
    0.42
    getContentPane
    0.34
     viernes
    0.33
     extiende
    0.33
    INCLUDED
    0.32
     thats
    0.32
    LayoutPanel
    0.32
    Activations Density 0.001%

    No Known Activations