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. 25-GEMMASCOPE-RES-16K
    6. 1839
    Prev
    Next
    INDEX
    Explanations

    references to public-private partnerships and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.64
     المعيارى
    -0.62
    Geplaatst
    -0.57
     manuals
    -0.57
     intptr
    -0.57
     pinulongan
    -0.56
    Autoritní
    -0.54
    UrlResolution
    -0.54
    DispatchToProps
    -0.53
     المعرف
    -0.52
    POSITIVE LOGITS
     developers
    1.22
     developer
    1.18
    Developers
    1.04
     redevelopment
    1.03
     Developers
    1.01
     construction
    1.01
     development
    1.00
    Developer
    0.99
    developer
    0.95
     Developer
    0.92
    Activations Density 0.465%

    No Known Activations