© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14985
    Prev
    Next
    INDEX
    Explanations

    symbols that indicate structure or formatting within written content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.99
     ProtoMessage
    -0.93
     ExecuteAsync
    -0.89
     kasarigan
    -0.89
    IsMutable
    -0.88
     queſta
    -0.88
    ſchaft
    -0.84
    DeleteBehavior
    -0.81
    
    -0.81
     ब्रेकडाउन
    -0.81
    POSITIVE LOGITS
    I
    0.48
    [toxicity=0]
    0.45
    The
    0.42
        
    0.41
    //
    0.40
            
    0.40
     
    0.38
    You
    0.37
     nghị
    0.37
                
    0.37
    Activations Density 0.531%

    No Known Activations