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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 57458
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and operational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InitVars
    -1.01
     BorderRadius
    -0.93
    Hentet
    -0.83
     joaat
    -0.81
    mybatisplus
    -0.79
    AsUp
    -0.79
     Cress
    -0.78
    outState
    -0.78
     EdgeInsets
    -0.76
     FontWeight
    -0.76
    POSITIVE LOGITS
    ↵
    0.96
    <eos>
    0.76
    	
    0.69
    		
    0.68
        
    0.68
    <h3>
    0.67
            
    0.65
    <h2>
    0.63
    <tr>
    0.59
    ↵↵
    0.58
    Activations Density 0.007%

    No Known Activations