© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 99187
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the ordering of items or references to inventions

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

    on June or July

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     estekak
    -1.01
     autorytatywna
    -1.00
    oa̍t
    -0.98
    Autoritní
    -0.94
     kaarangay
    -0.92
     propOrder
    -0.90
     kasarigan
    -0.90
     transférez
    -0.87
     мәкал
    -0.86
     Италијани
    -0.85
    POSITIVE LOGITS
    The
    0.49
     the
    0.49
     also
    0.46
    Also
    0.42
     
    0.40
    -
    0.40
    There
    0.40
    In
    0.40
    Alternatively
    0.38
    _
    0.38
    Activations Density 0.065%

    No Known Activations