© 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. 24-GEMMASCOPE-RES-16K
    11. 763
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "piece" in different contexts

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

    "piece" or "pieces"

    np_acts-logits-general · gemini-2.0-flash

    piece or pieces followed by "of"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدیا
    -0.64
    liferay
    -0.60
    MemoryWarning
    -0.60
     utafitiHapana
    -0.57
     NavController
    -0.56
     PeEnEo
    -0.55
    Cyfarwyddwr
    -0.54
    Schedulers
    -0.54
    NamedQueries
    -0.53
    ératures
    -0.52
    POSITIVE LOGITS
     piece
    1.39
     pieces
    1.36
     Piece
    1.21
     PIECE
    1.16
    piece
    1.16
     Pieces
    1.14
    Piece
    1.10
    Pieces
    1.03
    pieces
    0.98
     pieza
    0.95
    Activations Density 0.135%

    No Known Activations