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. 0-GEMMASCOPE-RES-16K
    6. 6351
    Prev
    Next
    INDEX
    Explanations

    references to specific towns or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.68
     regolare
    -0.62
     elétrica
    -0.61
     onResume
    -0.60
    CMYK
    -0.60
     NDEBUG
    -0.60
    MenuInflater
    -0.59
    bayes
    -0.59
    فایل‌لار
    -0.59
    ExtendWith
    -0.57
    POSITIVE LOGITS
    town
    0.83
    TOWN
    0.74
    Town
    0.72
    own
    0.70
     Town
    0.68
     prototype
    0.65
     Paglinawan
    0.65
     TOWN
    0.60
     proto
    0.60
    bg
    0.58
    Activations Density 0.092%

    No Known Activations