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. 22-GEMMASCOPE-RES-16K
    6. 16050
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to "pieces" in various contexts

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

    "piece" followed by "of"

    np_acts-logits-general · gemini-2.0-flash

    piece of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 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
    •Steering experiments: Gemma 2-2B / 10-GEMMASCOPE-RES-16K

    No Comments

    Negative Logits
     Wikispecies
    -0.84
    (!__
    -0.77
     iſt
    -0.77
    tagHelperRunner
    -0.74
     nahilalakip
    -0.73
     theſe
    -0.72
     ſeveral
    -0.71
     Normdatei
    -0.71
     leaſt
    -0.70
    Попис
    -0.70
    POSITIVE LOGITS
     pieces
    1.58
     Pieces
    1.52
    Pieces
    1.45
     Piece
    1.30
     piece
    1.29
    pieces
    1.24
     PIECE
    1.19
    Piece
    1.15
    meal
    1.10
    piece
    0.99
    Activations Density 0.090%

    No Known Activations