© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8251
    Prev
    Next
    INDEX
    Explanations

    starting and ending tokens, indicating the beginnings and endings of distinct sections or paragraphs within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.93
    GOTREF
    -0.86
    IntoConstraints
    -0.81
    AccessorTable
    -0.80
    XmlAccessType
    -0.80
    expandindo
    -0.79
    MessageTagHelper
    -0.78
    featureID
    -0.78
    DockStyle
    -0.74
    出版年
    -0.74
    POSITIVE LOGITS
    .
    0.38
      
    0.33
     
    0.24
    USA
    0.24
     USA
    0.23
    SM
    0.23
     in
    0.23
     spraw
    0.23
    ,
    0.23
     وذلك
    0.22
    Activations Density 0.763%

    No Known Activations