© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 7701
    Prev
    Next
    INDEX
    Explanations

    references to locations and organizations associated with Seattle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -0.50
     ivelany
    -0.47
    ɵɵ
    -0.46
    ⤹
    -0.45
     informée
    -0.44
     Gestão
    -0.44
    Personensuche
    -0.43
     Hunan
    -0.42
     hinweg
    -0.41
     contemporaine
    -0.41
    POSITIVE LOGITS
     Seattle
    1.63
    Seattle
    1.44
     Puget
    1.16
    seattle
    1.14
     Tacoma
    1.08
     Seahawks
    0.94
     Rainier
    0.91
     Bellingham
    0.88
     Spokane
    0.86
    ellingham
    0.85
    Activations Density 0.257%

    No Known Activations