© 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. 9-GEMMASCOPE-RES-131K
    11. 5719
    Prev
    Next
    INDEX
    Explanations

    references to jugs and related terminology

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

    subjugation

    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
     ACI
    -0.44
     Alamy
    -0.44
     Ernst
    -0.44
     Kaspersky
    -0.44
    qai
    -0.43
     Flach
    -0.42
     Stefani
    -0.42
     Stanton
    -0.41
    Carson
    -0.41
    afari
    -0.41
    POSITIVE LOGITS
     jug
    2.25
     Jug
    2.16
    Jug
    2.13
    jug
    1.99
     jugs
    1.48
     juggling
    1.28
     jugu
    0.77
     juger
    0.73
    ug
    0.70
     Gug
    0.70
    Activations Density 0.002%

    No Known Activations