© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12652
    Prev
    Next
    INDEX
    Explanations

    references to personal preferences and favorite things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſind
    -0.75
     vooz
    -0.73
     queſta
    -0.72
     myſelf
    -0.71
     $_(
    -0.71
     ſte
    -0.70
     ſche
    -0.70
     Monfieur
    -0.69
    RectangleBorder
    -0.69
     Infór
    -0.69
    POSITIVE LOGITS
     favorite
    1.70
    favorite
    1.58
     Favorite
    1.56
    Favorite
    1.54
     favourite
    1.50
     FAVORITE
    1.36
    favourite
    1.34
     Favourite
    1.33
     favorites
    1.31
    Favourite
    1.31
    Activations Density 0.098%

    No Known Activations