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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3450
    Prev
    Next
    INDEX
    Explanations

    phrases related to the process of creating or producing something

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ajinan
    -0.45
    WebServlet
    -0.44
    Tikang
    -0.43
    ///</
    -0.42
    utory
    -0.40
    setInitial
    -0.40
    copg
    -0.40
    徊
    -0.39
     Viss
    -0.39
    カバー
    -0.39
    POSITIVE LOGITS
    addComponent
    0.54
    Parcelize
    0.48
     autorytatywna
    0.48
    sequelize
    0.44
    BufferException
    0.44
     MutableLiveData
    0.42
     betweenstory
    0.40
     Drapeau
    0.39
     disambiguazione
    0.39
    دانشنامهٔ
    0.39
    Activations Density 0.196%

    No Known Activations