© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 14425
    Prev
    Next
    INDEX
    Explanations

    instances of numerical or quantitative references, particularly involving counts or measures related to cases, options, groups, or mutations

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

    two cases

    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
     all
    -0.43
     tất
    -0.39
     всех
    -0.35
     various
    -0.34
    各种
    -0.34
     Bautista
    -0.33
     Various
    -0.32
    verschluss
    -0.32
     wszystkich
    -0.31
     всіх
    -0.31
    POSITIVE LOGITS
     two
    0.96
    two
    0.94
     ujednoznacz
    0.89
     deux
    0.85
    Two
    0.84
     zwei
    0.84
     zweier
    0.81
     TWO
    0.80
     beiden
    0.80
     dwóch
    0.79
    Activations Density 0.463%

    No Known Activations