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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 38919
    Prev
    Next
    INDEX
    Explanations

    instances of parentheses and the word "née" related to names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Affaires
    -0.29
     flex
    -0.28
     put
    -0.27
     instead
    -0.27
    ,
    -0.26
     juntas
    -0.25
     Gebrauch
    -0.25
    ChildScrollView
    -0.25
     tramo
    -0.24
     puro
    -0.24
    POSITIVE LOGITS
     مرئيه
    0.85
     nakalista
    0.81
    хьтан
    0.72
    LookAnd
    0.71
     autorytatywna
    0.68
    CppMethod
    0.67
     propOrder
    0.67
    niſſe
    0.64
     geſch
    0.64
    ьаж
    0.64
    Activations Density 0.001%

    No Known Activations