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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10475
    Prev
    Next
    INDEX
    Explanations

    occurrences of "Tu" in various contexts

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

    Followed by punctuation or special characters

    np_acts-logits-general · gemini-2.0-flash

    the letter sequence 'tu'

    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
    Connection
    -0.38
     établir
    -0.37
     глаз
    -0.35
     URL
    -0.35
    Access
    -0.34
     Connection
    -0.33
     taşı
    -0.33
     oči
    -0.32
     ​
    -0.32
    connection
    -0.32
    POSITIVE LOGITS
     autorytatywna
    0.80
    Tikang
    0.63
     незавершена
    0.63
     виправивши
    0.63
     kasarigan
    0.61
    WebElementEntity
    0.60
    usercontent
    0.60
     AssemblyTitle
    0.59
    ThroughAttribute
    0.58
    
    0.58
    Activations Density 0.034%

    No Known Activations