Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11368
    Prev
    Next
    INDEX
    Explanations

    instances of the word "over"

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

    phrases indicating an action or state spanning an extent, especially over a time period, quantity, or repeated occurrence.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */].
    -0.46
    Princip
    -0.45
    Eins
    -0.42
     Cactus
    -0.41
    itects
    -0.41
     Eins
    -0.40
     princip
    -0.40
     Principals
    -0.40
     Citron
    -0.40
     tango
    -0.39
    POSITIVE LOGITS
     over
    1.15
     Over
    1.09
    over
    1.09
     OVER
    1.05
    Over
    1.01
    kover
    0.89
    OVER
    0.89
     över
    0.83
     über
    0.78
     Overton
    0.74
    Activations Density 0.167%

    No Known Activations