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. 11-GEMMASCOPE-RES-16K
    6. 5944
    Prev
    Next
    INDEX
    Explanations

    references to historical events and their timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imread
    -0.53
     Sur
    -0.48
     mód
    -0.47
     Strike
    -0.45
     Striking
    -0.45
     giriş
    -0.45
     Day
    -0.45
     click
    -0.45
     halfway
    -0.44
     Spalding
    -0.44
    POSITIVE LOGITS
     period
    0.79
    HtmlAttribute
    0.76
     periods
    0.73
    AddTagHelper
    0.71
     AssemblyTitle
    0.70
     useAppContext
    0.69
    にかけて
    0.67
    period
    0.66
     Roskov
    0.66
     perioden
    0.65
    Activations Density 0.682%

    No Known Activations