© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 74320
    Prev
    Next
    INDEX
    Explanations

    references to data structures and items related to programming, especially in the context of product and category management

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

    foreign words

    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
     autorytatywna
    -0.67
    AnimationsModule
    -0.61
     BrowserModule
    -0.59
    MigrationBuilder
    -0.56
    rawDesc
    -0.56
    SharedDtor
    -0.55
    StoreMessageInfo
    -0.54
    webElementXpaths
    -0.53
     <=",
    -0.53
    Hozzáférés
    -0.50
    POSITIVE LOGITS
     Ankunft
    0.42
    ariConfig
    0.38
    laması
    0.38
     abbiano
    0.37
    ducción
    0.37
     strutture
    0.36
     ragazze
    0.36
     livros
    0.36
    SEGUIR
    0.36
     skues
    0.35
    Activations Density 0.005%

    No Known Activations