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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 75425
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "give" and its variations, indicating a focus on the concept of providing or offering something

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

    the verb give

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jsoup
    -0.50
    rowData
    -0.48
    dafx
    -0.46
    selectedItem
    -0.45
     chanted
    -0.45
    columnIndex
    -0.43
    httpd
    -0.42
    funcs
    -0.42
     Lawton
    -0.41
    maco
    -0.41
    POSITIVE LOGITS
    give
    1.34
    Give
    1.27
     Give
    1.24
     give
    1.22
     GIVE
    1.13
    Giving
    1.09
     Giving
    1.07
    GIVE
    1.07
    gives
    1.06
     Gives
    1.06
    Activations Density 0.065%

    No Known Activations