© 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. 11-GEMMASCOPE-RES-16K
    11. 12818
    Prev
    Next
    INDEX
    Explanations

    terminologies related to programming and technology concepts, especially focusing on performance, efficiency, and issues concerning systems or applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     –,
    -0.51
     nonnegative
    -0.49
    ​—
    -0.48
     —,
    -0.46
     dieselbe
    -0.43
     به‌عنوان
    -0.42
     
    -0.40
    . 
    -0.40
     dasselbe
    -0.38
     _:
    -0.38
    POSITIVE LOGITS
    
    0.83
     didalam
    0.81
     diatas
    0.81
     loosing
    0.78
     GenerationType
    0.76
    AddTagHelper
    0.70
     perchè
    0.70
    EndInit
    0.69
    cupertino
    0.69
     dimana
    0.68
    Activations Density 2.377%

    No Known Activations