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. 8203
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntactic elements 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_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
     queſta
    -1.26
     increí
    -1.09
    ſelben
    -1.05
     surla
    -1.02
    ſammen
    -1.00
    ſchaft
    -0.99
     Biôgrafia
    -0.98
    ementara
    -0.96
    iſchen
    -0.95
    ðsíða
    -0.95
    POSITIVE LOGITS
    <tr>
    0.59
     
    0.56
    '
    0.49
     otherwise
    0.48
        
    0.48
    /*
    0.48
    else
    0.47
    //
    0.47
    hline
    0.47
    ...
    0.47
    Activations Density 0.007%

    No Known Activations