© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 52081
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "working."

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

    working in, with, for, under, at, as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transparencia
    -0.55
    nalpot
    -0.50
    <bos>
    -0.50
     coroa
    -0.49
     autonomía
    -0.49
     dignidad
    -0.48
     Kompetenz
    -0.48
     bahía
    -0.48
     espont
    -0.48
    acamata
    -0.47
    POSITIVE LOGITS
    working
    1.97
     working
    1.93
    Working
    1.92
     Working
    1.90
     WORKING
    1.71
    WORKING
    1.70
    orking
    1.11
     trabajando
    1.05
    Worked
    0.98
    worked
    0.96
    Activations Density 0.011%

    No Known Activations