Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 10588
    Prev
    Next
    INDEX
    Explanations

    specific player positions in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     acrylique
    -0.54
    EndContext
    -0.54
    admin
    -0.52
    ValueStyle
    -0.51
    roveň
    -0.51
    ograms
    -0.51
     Réponses
    -0.51
     okuyayım
    -0.50
     communauté
    -0.50
    ustimmung
    -0.50
    POSITIVE LOGITS
    BeginInit
    0.60
     position
    0.60
    Demografía
    0.57
     AssemblyTitle
    0.53
     tandem
    0.53
    inaison
    0.53
    TagMode
    0.51
     offensi
    0.51
     positions
    0.50
    XmlEnum
    0.50
    Activations Density 0.142%

    No Known Activations