© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16228
    Prev
    Next
    INDEX
    Explanations

    phrases related to division and fragmentation

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

    breaking apart

    np_acts-logits-general · gemini-2.0-flash

    into pieces or fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     Normdatei
    -0.60
     سكانية
    -0.54
     gynnwys
    -0.51
    itamente
    -0.47
    цездатний
    -0.47
     ويكيپيديا
    -0.47
    amai
    -0.45
    jacent
    -0.45
    Vezi
    -0.45
    dijk
    -0.44
    POSITIVE LOGITS
     pieces
    2.06
     Pieces
    1.80
     fragments
    1.77
    pieces
    1.75
    Pieces
    1.67
     piece
    1.61
     split
    1.57
     fragment
    1.55
     fragmented
    1.54
     parts
    1.52
    Activations Density 0.619%

    No Known Activations