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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 68319
    Prev
    Next
    INDEX
    Explanations

    phrases that express the concept of making processes simpler or more manageable

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

    easier to

    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
     verksamhet
    -0.52
     häls
    -0.51
     henkil
    -0.51
    akaian
    -0.50
     kandang
    -0.50
     kemasan
    -0.49
     proyec
    -0.48
     QtWidgets
    -0.48
    yecek
    -0.47
     produkter
    -0.47
    POSITIVE LOGITS
    Easier
    1.16
    easier
    1.12
     Easier
    1.11
     easier
    1.06
     Ease
    0.91
    easy
    0.86
    Easy
    0.83
     Easy
    0.82
    Ease
    0.81
     ease
    0.78
    Activations Density 0.018%

    No Known Activations