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. 5-GEMMASCOPE-RES-16K
    6. 10458
    Prev
    Next
    INDEX
    Explanations

    phrases that describe actions of managing or achieving tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vastu
    -0.57
    exitRule
    -0.56
    पे
    -0.53
    dej
    -0.51
     Decatur
    -0.51
     AspNetCore
    -0.51
    cotta
    -0.51
    fjspx
    -0.51
    äns
    -0.50
     responsibility
    -0.50
    POSITIVE LOGITS
     lograron
    1.12
     successfully
    1.07
     logra
    1.02
     logrado
    1.02
     conseguido
    1.00
     réuss
    1.00
     achieved
    0.98
     удалось
    0.97
     conseguiu
    0.96
     logró
    0.96
    Activations Density 0.181%

    No Known Activations