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. 5-GEMMASCOPE-RES-16K
    6. 11886
    Prev
    Next
    INDEX
    Explanations

    quotes and citations from articles or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPATH
    -0.81
     bezeichneter
    -0.61
    sizeCache
    -0.61
    modelBuilder
    -0.59
     RSSSF
    -0.59
    IconModule
    -0.58
     abandonné
    -0.54
     gainera
    -0.54
    byes
    -0.53
     الرياضيه
    -0.52
    POSITIVE LOGITS
     quoted
    1.07
     quote
    1.05
     excerpt
    1.03
     verbatim
    0.98
     quotes
    0.97
     quotation
    0.95
     excerpts
    0.95
     Quoted
    0.93
    quote
    0.92
     citation
    0.87
    Activations Density 0.352%

    No Known Activations