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. 75358
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizing or making arrangements

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

    arranging things, events, or actions

    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
    propTypes
    -0.39
    IconModule
    -0.39
     nemici
    -0.35
     nemico
    -0.35
    utant
    -0.35
     cães
    -0.35
    胜
    -0.35
    ẢN
    -0.35
     consumidor
    -0.35
     currentUser
    -0.35
    POSITIVE LOGITS
     arrange
    0.93
    arrange
    0.88
     arranged
    0.81
     arranging
    0.81
     arranges
    0.80
     arrangements
    0.75
     organise
    0.73
     Arrange
    0.72
     arrang
    0.72
     ARRANG
    0.71
    Activations Density 0.018%

    No Known Activations