© 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. 9-GEMMASCOPE-RES-16K
    11. 14912
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "the" and other terms indicating quantification or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dries
    -0.81
     rubs
    -0.69
     cools
    -0.68
    囗
    -0.66
     softens
    -0.65
     parteci
    -0.63
     breathes
    -0.63
     resonates
    -0.58
     melts
    -0.58
     rots
    -0.58
    POSITIVE LOGITS
     use
    0.81
     increase
    0.77
     sự
    0.73
     việc
    0.70
    ệc
    0.70
    ajiban
    0.65
     simultaneous
    0.61
    การ
    0.60
     study
    0.60
     '\\;'
    0.59
    Activations Density 0.932%

    No Known Activations