Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 5007
    Prev
    Next
    INDEX
    Explanations

    nutritional benefits and bioactive compounds in plants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſee
    -0.57
     unsuccessful
    -0.55
     "..\..\
    -0.55
     mourut
    -0.55
     ſhall
    -0.53
    stí
    -0.53
     Klicken
    -0.53
     Orrell
    -0.52
     tibi
    -0.50
     avoit
    -0.49
    POSITIVE LOGITS
    पया
    0.62
    badlogic
    0.55
    pyx
    0.53
    indd
    0.53
    Abitanti
    0.52
    codehaus
    0.52
     mediator
    0.51
    gehalt
    0.51
     content
    0.50
    twimg
    0.50
    Activations Density 0.296%

    No Known Activations