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. 13-GEMMASCOPE-RES-16K
    6. 14472
    Prev
    Next
    INDEX
    Explanations

    references to quantity or number of occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Slf
    -0.77
     tasche
    -0.73
     vertes
    -0.69
     esetén
    -0.69
     digitais
    -0.68
    לית
    -0.66
     laikā
    -0.63
     bolig
    -0.62
    yra
    -0.61
     grafica
    -0.61
    POSITIVE LOGITS
     dozen
    1.23
     few
    1.06
    dozen
    1.02
     FEW
    1.00
     hundred
    0.95
     wenige
    0.94
     CreateTagHelper
    0.92
    few
    0.90
    FieldBuilder
    0.88
     wenigen
    0.85
    Activations Density 0.072%

    No Known Activations