© 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. 36-GEMMASCOPE-RES-16K
    6. 7643
    Prev
    Next
    INDEX
    Explanations

    the presence of syntax errors in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.65
    featureID
    -0.63
     незавершена
    -0.60
    醐
    -0.60
    LLocation
    -0.60
    msgTypes
    -0.59
    клопе
    -0.58
    localctx
    -0.57
     DBNull
    -0.56
     queſta
    -0.55
    POSITIVE LOGITS
        
    0.72
     
    0.52
    	
    0.43
       
    0.41
    İstinadlar
    0.40
     íntimo
    0.40
    Either
    0.39
     ciudadana
    0.39
     enví
    0.36
     chrétien
    0.36
    Activations Density 0.675%

    No Known Activations