© 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. 25-GEMMASCOPE-RES-16K
    11. 1346
    Prev
    Next
    INDEX
    Explanations

    high-frequency, single tokens that contribute to the overall sentiment or tone of the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.67
     فريبيس
    -0.60
    ItemBackground
    -0.56
    ecture
    -0.54
    IRQn
    -0.53
    xase
    -0.51
    EndInit
    -0.51
    ژاد
    -0.50
    rhosis
    -0.50
    Fazit
    -0.50
    POSITIVE LOGITS
     seven
    0.82
     eight
    0.80
     nine
    0.78
     six
    0.77
    thousands
    0.75
     thirteen
    0.74
     five
    0.74
     sixteen
    0.73
     least
    0.72
     thirty
    0.72
    Activations Density 0.205%

    No Known Activations