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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-GEMMASCOPE-RES-16K
    6. 3340
    Prev
    Next
    INDEX
    Explanations

    keywords related to bags and carrying items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    bags or containers

    np_acts-logits-general · gemini-2.0-flash

    bag or backpack

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.72
     समीक्षाओं
    -0.70
    хьтан
    -0.62
    eradish
    -0.62
     BoxFit
    -0.61
     PyLong
    -0.60
     Савезне
    -0.59
    +#+#
    -0.59
    ดาว
    -0.58
     الرياضيه
    -0.58
    POSITIVE LOGITS
     bag
    1.89
     bags
    1.77
    bag
    1.57
     Bag
    1.54
     Bags
    1.53
    bags
    1.49
    Bag
    1.49
    Bags
    1.41
     backpack
    1.37
     BAG
    1.33
    Activations Density 0.136%

    No Known Activations