Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 7103
    Prev
    Next
    INDEX
    Explanations

    patterns representing structure and organization within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ),
    
    -0.64
     );
    
    -0.63
     -->
    
    -0.62
    RegressionTest
    -0.61
     ");
    
    -0.59
    原始内容存档于
    -0.59
    ")]
    
    -0.57
     "),
    -0.56
    DataAnnotations
    -0.55
     )
    
    -0.55
    POSITIVE LOGITS
    }
    0.93
    <unused63>
    0.76
    <unused62>
    0.74
    	
    0.74
    <unused61>
    0.72
    <unused60>
    0.70
      
    0.69
    }//
    0.61
        
    0.60
    ?}
    0.59
    Activations Density 0.102%

    No Known Activations