© 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-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 8307
    Prev
    Next
    INDEX
    Explanations

    quantitative references, specifically numbers and their occurrences in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chevalier
    -0.65
     fédé
    -0.63
     Nacionales
    -0.63
    hésite
    -0.61
    StoreMessageInfo
    -0.61
     Zuge
    -0.60
    Tikang
    -0.59
     savages
    -0.57
     diccionario
    -0.57
     magari
    -0.54
    POSITIVE LOGITS
     two
    0.90
     three
    0.84
     dozen
    0.81
     four
    0.79
    two
    0.78
     zwei
    0.74
    zwei
    0.73
    dozen
    0.72
     deux
    0.70
    three
    0.70
    Activations Density 0.690%

    No Known Activations