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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 120879
    Prev
    Next
    INDEX
    Explanations

    percentage values and their related impacts on attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     mukana
    -0.43
     vícti
    -0.43
     interactiva
    -0.41
     informée
    -0.40
     kanssa
    -0.39
    hithe
    -0.38
    spesies
    -0.38
     cepillo
    -0.36
     cucchiaio
    -0.36
     testigo
    -0.36
    POSITIVE LOGITS
     boost
    0.66
     increase
    0.56
     boosts
    0.54
     aumenta
    0.52
    increase
    0.50
     boosting
    0.50
     увели
    0.50
     propOrder
    0.49
     InputDecoration
    0.49
     increases
    0.48
    Activations Density 0.019%

    No Known Activations