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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 2771
    Prev
    Next
    INDEX
    Explanations

    parentheses and their corresponding usage in code syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })*/
    -0.91
    )))));
    -0.87
     intptr
    -0.84
    ]));
    
    -0.83
    });*/
    -0.83
    ']]
    -0.82
    '));
    
    -0.82
    }))
    
    -0.81
    };*/
    -0.81
    %");
    -0.81
    POSITIVE LOGITS
     considérons
    0.51
    proz
    0.49
     douceur
    0.49
     saliv
    0.49
    setPointSize
    0.49
     légitime
    0.48
     Económica
    0.47
     butts
    0.46
     salada
    0.45
     pitié
    0.45
    Activations Density 0.038%

    No Known Activations