© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 8335
    Prev
    Next
    INDEX
    Explanations

    references to Hong Kong and its geographical features

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

    "Hong" followed by "Kong"

    np_acts-logits-general · gemini-2.0-flash

    Hong Kong

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ètres
    -0.57
    koľvek
    -0.52
    EndProject
    -0.51
    reuters
    -0.49
    rasil
    -0.48
    שב
    -0.47
    ETIES
    -0.47
     Marks
    -0.46
    cetti
    -0.46
    autoconfigure
    -0.45
    POSITIVE LOGITS
     Kong
    1.12
    Kong
    1.03
     KONG
    0.82
    CloseOperation
    0.81
     kong
    0.79
    }],
    0.72
    ).</
    0.67
    aarrggbb
    0.67
    kong
    0.65
    :+:
    0.64
    Activations Density 0.113%

    No Known Activations