© 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. 10-GEMMASCOPE-RES-16K
    6. 6407
    Prev
    Next
    INDEX
    Explanations

    references to the United States and its associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endforeach
    -0.47
    RRect
    -0.47
     réfugiés
    -0.44
     CommonModule
    -0.44
    WritableDatabase
    -0.43
    balleur
    -0.43
    zeß
    -0.43
     verrou
    -0.43
    󠁢
    -0.43
    érables
    -0.40
    POSITIVE LOGITS
    在美国
    0.91
     American
    0.90
     America
    0.85
     американ
    0.85
     USA
    0.82
     Amerikaanse
    0.81
    アメリカ
    0.81
     amerikanischen
    0.81
    アメリカの
    0.80
     ameryka
    0.79
    Activations Density 1.393%

    No Known Activations