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-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 6315
    Prev
    Next
    INDEX
    Explanations

    the word "United" when it refers to the United States

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Orissa
    -0.87
    évaluateur
    -0.87
     Roskov
    -0.87
     Meksiku
    -0.84
     NSCoder
    -0.81
    InjectAttribute
    -0.77
     ModelExpression
    -0.76
     BORROW
    -0.75
    NameInMap
    -0.75
    featureID
    -0.73
    POSITIVE LOGITS
     United
    3.55
    United
    3.31
     UNITED
    2.83
    UNITED
    2.58
    united
    2.32
     united
    2.25
     Vereinigten
    1.84
     Utd
    1.46
     Verenigde
    1.45
     Vereinigte
    1.41
    Activations Density 0.071%

    No Known Activations