© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14226
    Prev
    Next
    INDEX
    Explanations

    constructs and operations related to data manipulation and type conversion in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Butterfield
    -0.28
     viņ
    -0.26
     
    -0.25
     faltan
    -0.24
    ılmış
    -0.24
    PickerController
    -0.24
    ルド
    -0.24
     ring
    -0.24
    collectionView
    -0.23
     air
    -0.23
    POSITIVE LOGITS
    XmlAccessorType
    0.77
     defaultstate
    0.73
    ロウィン
    0.71
    awtextra
    0.65
    /*-
    0.65
     propOrder
    0.63
     ویکی‌پدی
    0.63
     Administrativna
    0.63
    IntoConstraints
    0.63
    fjspx
    0.62
    Activations Density 0.986%

    No Known Activations