© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8643
    Prev
    Next
    INDEX
    Explanations

    programming function definitions and related keywords

    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
     
    -0.47
        
    -0.26
     np
    -0.26
    ​
    -0.25
     [
    -0.24
    	
    -0.24
       
    -0.22
            
    -0.22
     this
    -0.22
    SuppressWarnings
    -0.22
    POSITIVE LOGITS
     snippetHide
    1.14
     CreateTagHelper
    1.13
    ValueStyle
    1.05
    IntoConstraints
    1.01
    OGND
    1.01
    ſicht
    1.01
    ंदीखरीदारी
    0.99
     незавершена
    0.96
     ब्रेकडाउन
    0.94
    <unused14>
    0.94
    Activations Density 0.684%

    No Known Activations