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. 5245
    Prev
    Next
    INDEX
    Explanations

    URLs and related web content structures

    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
     '\\;'
    -0.67
    ItemBackground
    -0.65
    orsese
    -0.64
     vPvB
    -0.62
     Meksiku
    -0.59
    intios
    -0.58
    Personendaten
    -0.57
    Хьажоргаш
    -0.57
    TintMode
    -0.56
     incontinence
    -0.56
    POSITIVE LOGITS
    '},
    
    0.67
     IBOutlet
    0.62
     CGRectMake
    0.59
     RoutedEventArgs
    0.56
    hatenablog
    0.56
    %"),
    0.54
    
    0.53
    .~(\
    0.52
     UITableView
    0.52
    UITableView
    0.51
    Activations Density 0.157%

    No Known Activations