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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 769
    Prev
    Next
    INDEX
    Explanations

    features and specifications related to automotive technology and design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.94
    曖昧さ回避
    -0.79
     ujednoznacz
    -0.79
    exitRule
    -0.76
    afficheront
    -0.72
    Spoljašnje
    -0.71
     gynhyrchwyd
    -0.70
     cherchés
    -0.70
     purpoſe
    -0.70
    tagHelperRunner
    -0.68
    POSITIVE LOGITS
     optional
    0.96
     option
    0.95
     options
    0.85
    option
    0.81
     standard
    0.80
     Optional
    0.79
    optional
    0.76
     Option
    0.76
     configuration
    0.73
     opsi
    0.73
    Activations Density 0.173%

    No Known Activations