© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 2658
    Prev
    Next
    INDEX
    Explanations

    specific mathematical symbols and notations used in equations and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.65
     &
    -0.61
    ,
    -0.61
    .
    -0.60
     (
    -0.60
     ...
    -0.57
    原始内容存档于
    -0.57
     ri
    -0.55
     برابوك
    -0.54
    tokio
    -0.52
    POSITIVE LOGITS
     ainfi
    0.94
     becauſe
    0.85
     Theſe
    0.80
     auffi
    0.79
     zelve
    0.77
    ㅗ
    0.77
     chofe
    0.76
     Pizz
    0.76
     againſt
    0.76
     Toibin
    0.75
    Activations Density 0.911%

    No Known Activations