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. 8214
    Prev
    Next
    INDEX
    Explanations

    references to wild type (WT) and mutant organisms in a scientific 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
    Clik
    -0.66
    httphttps
    -0.65
     surla
    -0.60
    assing
    -0.59
    achting
    -0.57
     Pizz
    -0.56
     للاسماء
    -0.56
     Navigation
    -0.56
    ication
    -0.54
    pagation
    -0.54
    POSITIVE LOGITS
    WT
    0.75
     WT
    0.69
    wt
    0.64
     wt
    0.64
     Mutant
    0.57
    Mutant
    0.57
     mutant
    0.56
    mutant
    0.54
    Wt
    0.54
     createState
    0.50
    Activations Density 0.024%

    No Known Activations