© 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. 121468
    Prev
    Next
    INDEX
    Explanations

    references to retail locations or showrooms

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

    show quality restoration

    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
     Taco
    -0.54
     Pape
    -0.52
    httphttps
    -0.52
     canadien
    -0.50
    Canadian
    -0.50
     veci
    -0.49
     Patrick
    -0.49
    Taco
    -0.49
     celtic
    -0.48
     lege
    -0.48
    POSITIVE LOGITS
     showroom
    2.13
     Showroom
    1.95
    showroom
    1.93
     SHOW
    0.86
     Show
    0.85
     show
    0.85
    Show
    0.84
    show
    0.82
     showcase
    0.82
    SHOW
    0.77
    Activations Density 0.001%

    No Known Activations