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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 14959
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "pieces" or "piece" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.78
    Попис
    -0.75
    MLLoader
    -0.70
    (!__
    -0.69
     InputDecoration
    -0.68
    خواندن
    -0.68
     SIMBAD
    -0.67
    📖
    -0.67
     ")");
    -0.67
     ExecuteAsync
    -0.65
    POSITIVE LOGITS
     pieces
    3.87
     Pieces
    3.58
     piece
    3.37
    Pieces
    3.35
    pieces
    3.32
     Piece
    3.05
     PIECE
    2.97
    piece
    2.97
    Piece
    2.92
    PIECE
    2.37
    Activations Density 0.051%

    No Known Activations