© 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. 20-GEMMASCOPE-RES-16K
    6. 4913
    Prev
    Next
    INDEX
    Explanations

    instances of comments or annotations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code-related documentation comments, specifically in programming languages like PHP or JavaScript.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -1.17
    parsedMessage
    -1.09
    出版年
    -1.09
    
    -1.06
    tvguidetime
    -1.05
     ब्रेकडाउन
    -1.05
    RegressionTest
    -1.04
     queſta
    -1.03
    featureID
    -1.00
     Roskov
    -0.97
    POSITIVE LOGITS
    //
    0.74
    ///
    0.66
     *
    0.60
    *
    0.56
    0
    0.56
    /*
    0.54
     
    0.53
    #
    0.51
    :
    0.51
        
    0.51
    Activations Density 0.061%

    No Known Activations