© 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. 15886
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and specific syntactical structures in code or markup

    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
    statusBar
    -0.57
    olo
    -0.54
    uzzi
    -0.54
     Sutherland
    -0.51
     stand
    -0.50
    ligg
    -0.50
    tein
    -0.50
    stand
    -0.50
     chính
    -0.49
     k
    -0.48
    POSITIVE LOGITS
     الرياضيه
    1.10
    })));
    0.97
    })();
    
    0.93
    ]));
    
    0.93
    ])));
    0.90
    }}$\\
    0.88
    __":
    
    0.88
    }))
    
    0.87
    .*;
    
    0.86
    ];
    
    0.85
    Activations Density 0.002%

    No Known Activations