© 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. 1-GEMMASCOPE-RES-16K
    11. 5865
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "More."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.67
     more
    -0.59
     long
    -0.57
     שוליים
    -0.55
    usermodel
    -0.55
     estimés
    -0.55
    Посилання
    -0.54
    ElementException
    -0.53
    んな
    -0.52
     ages
    -0.52
    POSITIVE LOGITS
     Many
    1.41
    Many
    1.18
     More
    1.15
     Most
    1.02
     Some
    1.02
     Few
    1.00
    Most
    0.97
    Few
    0.96
     Muchos
    0.95
     Much
    0.93
    Activations Density 0.086%

    No Known Activations