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. 8850
    Prev
    Next
    INDEX
    Explanations

    numerical data or references related to quantities and statistical measures

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

    mathematical comparisons and symbols

    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
    IUrlHelper
    -0.95
    httphttps
    -0.64
     autorytatywna
    -0.64
    ьаж
    -0.60
     ujednoznacz
    -0.58
     &___
    -0.57
    TRIBUN
    -0.56
    DIPSETTING
    -0.54
     Ih
    -0.53
    weightedMode
    -0.53
    POSITIVE LOGITS
     herida
    0.48
     húmedo
    0.47
     herido
    0.45
     silueta
    0.45
     enfance
    0.45
     bahía
    0.44
     religión
    0.43
     Jerusalén
    0.43
     república
    0.42
     secundario
    0.42
    Activations Density 0.551%

    No Known Activations