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. 12-GEMMASCOPE-RES-16K
    6. 12107
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and numerical calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.79
     propOrder
    -0.76
     asing
    -0.76
     kend
    -0.70
     AppBar
    -0.66
    bkz
    -0.65
    
    -0.65
     Paw
    -0.64
     initComponents
    -0.64
    isSet
    -0.63
    POSITIVE LOGITS
     Blatt
    0.81
     Alder
    0.78
     CUB
    0.76
     Eno
    0.71
     golem
    0.71
     Mete
    0.69
     Grou
    0.69
    AddField
    0.67
    Alder
    0.67
    cardname
    0.66
    Activations Density 1.327%

    No Known Activations