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. 23153
    Prev
    Next
    INDEX
    Explanations

    technical components and issues related to automotive engineering and transmissions

    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
     avulla
    -0.52
     coroa
    -0.52
     cerah
    -0.51
     elämä
    -0.51
     rând
    -0.50
     cuchara
    -0.49
     nacionales
    -0.49
     gruesa
    -0.48
     vergüenza
    -0.47
     ruinas
    -0.47
    POSITIVE LOGITS
     MainAxisSize
    0.85
     BoxDecoration
    0.62
    gdala
    0.60
     Autos
    0.59
    lapsingToolbar
    0.59
    NgModule
    0.57
     استنادى
    0.57
     ActionBar
    0.56
     AppCompatTheme
    0.56
    SceneManagement
    0.56
    Activations Density 0.023%

    No Known Activations