Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14508
    Prev
    Next
    INDEX
    Explanations

    references to people, locations, and organizations, especially in relation to the United States

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

    "American," "USA" or the United States

    np_acts-logits-general · gemini-2.0-flash

    American and USA references

    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
    colgante
    -0.46
    cartão
    -0.45
     Cement
    -0.41
     arrêt
    -0.41
     pretense
    -0.40
    Legături
    -0.40
     taşı
    -0.39
     CURLOPT
    -0.39
     debout
    -0.39
     étudiants
    -0.39
    POSITIVE LOGITS
     USA
    1.05
    在美国
    1.04
     American
    1.02
     America
    1.02
    🇺🇸
    0.98
     US
    0.98
    USA
    0.94
     американ
    0.94
    アメリカ
    0.93
    American
    0.92
    Activations Density 0.876%

    No Known Activations