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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9441
    Prev
    Next
    INDEX
    Explanations

    markup or formatting commands typically used in technical or scientific writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text followed by the letter Q

    np_acts-logits-general · gemini-2.0-flash

    agents or Q:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]));
    
    -0.86
    ())));
    -0.77
    }));
    
    -0.76
    }),
    
    -0.71
    ]),
    
    -0.71
    ()]
    
    -0.70
    ']));
    -0.70
    ()));
    
    -0.70
    )));
    
    -0.69
    <eos>
    -0.68
    POSITIVE LOGITS
    rrggbb
    1.11
    AsUp
    0.96
    IntoConstraints
    0.95
     étoient
    0.93
     Monfieur
    0.90
     brancas
    0.90
     varandra
    0.89
     florales
    0.89
     aikaa
    0.88
     Theſe
    0.87
    Activations Density 0.176%

    No Known Activations