© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7206
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal processes and opposition

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

    followed by "the."

    np_acts-logits-general · gemini-2.0-flash

    whole entire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.42
    แก่
    -0.37
    บ้าง
    -0.35
    ɵɵ
    -0.34
     disambiguazione
    -0.33
    ceğine
    -0.33
    Lähteet
    -0.31
    owymi
    -0.30
    mbals
    -0.30
     voici
    -0.29
    POSITIVE LOGITS
     entire
    2.66
     whole
    2.48
    whole
    2.25
    entire
    2.22
     Entire
    2.05
     ENTIRE
    1.99
    Entire
    1.99
    整个
    1.90
     WHOLE
    1.85
     ganze
    1.80
    Activations Density 0.625%

    No Known Activations