© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 861
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hold" and its variations in context

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

    "hold" and its inflections

    np_acts-logits-general · gemini-2.0-flash

    hold, held, holds, holding

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    Personensuche
    -0.63
    ➟
    -0.59
    CppMethod
    -0.57
     CommonModule
    -0.54
     Ames
    -0.50
     Sanger
    -0.50
     bParam
    -0.49
     gynhyrchwyd
    -0.48
    simpleType
    -0.48
     southwestern
    -0.48
    POSITIVE LOGITS
    hold
    1.10
     hold
    1.07
     Hold
    1.06
     Holding
    1.05
    Hold
    1.03
    held
    1.01
    holding
    1.01
     Holds
    0.99
    Holding
    0.99
     holds
    0.97
    Activations Density 0.071%

    No Known Activations