© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8560
    Prev
    Next
    INDEX
    Explanations

    patterns or sequences that indicate structured data or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.86
    AsUp
    -0.82
    ########.
    -0.76
     EClass
    -0.73
    fromnode
    -0.72
    featureID
    -0.72
    دانشنامهٔ
    -0.72
    argout
    -0.70
    <bos>
    -0.68
    pyplot
    -0.67
    POSITIVE LOGITS
                            
    2.29
                                
    1.98
                             
    1.87
                          
    1.84
                        
    1.80
                              
    1.77
                         
    1.73
                           
    1.73
                               
    1.70
    1.66
    Activations Density 0.159%

    No Known Activations