© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 11733
    Prev
    Next
    INDEX
    Explanations

    references to a specific person named Tony

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

    similar to "Tony"

    np_acts-logits-general · gemini-2.0-flash

    names like tony and anthony

    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
     HasFactory
    -0.47
    脚注の使い方
    -0.46
    reportWebVitals
    -0.45
    jewództ
    -0.43
    Predecesor
    -0.41
     numériques
    -0.41
     onItemClick
    -0.41
    ctober
    -0.40
     dépasser
    -0.39
    EnableWeb
    -0.39
    POSITIVE LOGITS
     Toni
    0.69
     TON
    0.68
    Tone
    0.61
    Toni
    0.60
     Tone
    0.59
     ton
    0.58
    Ton
    0.57
     Tones
    0.56
     tone
    0.56
     Tony
    0.56
    Activations Density 0.112%

    No Known Activations