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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 4989
    Prev
    Next
    INDEX
    Explanations

    technical specifications and performance features related to products, particularly electronic devices or vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.70
     AIAA
    -0.70
     sporad
    -0.68
     oldest
    -0.65
    billon
    -0.63
     Ephe
    -0.61
    tonode
    -0.60
    pulsar
    -0.60
     cappella
    -0.60
     strangest
    -0.60
    POSITIVE LOGITS
    Designed
    0.74
     unique
    0.69
     grazie
    0.69
     ensures
    0.68
     designed
    0.67
     Designed
    0.66
     grâce
    0.65
     Благодаря
    0.65
     unparalleled
    0.63
    designed
    0.62
    Activations Density 0.175%

    No Known Activations