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. 21-GEMMASCOPE-RES-16K
    6. 1029
    Prev
    Next
    INDEX
    Explanations

    references to the Ebola outbreak and its impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arakhand
    -0.57
    atchewan
    -0.54
    hamel
    -0.53
     coyote
    -0.51
     Pingback
    -0.51
    voerd
    -0.50
    issauga
    -0.49
    شهاد
    -0.49
     Uttarakhand
    -0.48
     Coyote
    -0.48
    POSITIVE LOGITS
     Liberia
    0.89
     Monro
    0.77
    Liber
    0.76
     autorytatywna
    0.75
     typelib
    0.74
     Liber
    0.73
    rungsseite
    0.68
     Nim
    0.67
    ########.
    0.62
    تفصیلات
    0.62
    Activations Density 0.066%

    No Known Activations