© 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. 10373
    Prev
    Next
    INDEX
    Explanations

    tourist-related activities and destinations

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

    Preceding "user" or related to the start of turn

    np_acts-logits-general · gemini-2.0-flash

    lunch and afternoon

    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
     mxArray
    -0.51
    Diweddarwch
    -0.50
     (!_
    -0.46
     Warne
    -0.46
    FailureListener
    -0.45
     wart
    -0.44
    findpost
    -0.43
     nightmares
    -0.42
    wur
    -0.42
    ences
    -0.42
    POSITIVE LOGITS
     recevrez
    0.47
     Económica
    0.43
     lunch
    0.42
    Lunch
    0.42
     Lunch
    0.42
    complexContent
    0.40
     almuerzo
    0.40
     afternoon
    0.40
     luncheon
    0.39
    午餐
    0.39
    Activations Density 0.037%

    No Known Activations