© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 58207
    Prev
    Next
    INDEX
    Explanations

    references to the United States and its various contexts, especially when related to entities, events, or statistics

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

    American places and nationalities

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     rallado
    -0.35
     néz
    -0.34
    CrossRef
    -0.33
     Accesorios
    -0.31
    vinilo
    -0.31
    ńczy
    -0.31
    cámara
    -0.31
     Hatton
    -0.31
     constater
    -0.30
    maksud
    -0.30
    POSITIVE LOGITS
    在美国
    1.15
    🇺🇸
    1.02
     America
    1.02
    America
    0.99
    American
    0.98
     USA
    0.96
     American
    0.96
    美国
    0.94
    USA
    0.93
    amerikanische
    0.92
    Activations Density 0.828%

    No Known Activations