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. 18-GEMMASCOPE-RES-16K
    6. 8643
    Prev
    Next
    INDEX
    Explanations

    code snippets related to function types and their classification in Python

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

    Code snippets related to Python

    np_acts-logits-general · gemini-2.0-flash

    Python django projects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]));
    
    -0.84
    )];
    
    -0.75
    ]);
    
    -0.70
    ']);
    
    -0.70
    AndEndTag
    -0.70
    '));
    
    -0.69
    ++){
    -0.69
    ++]
    -0.69
    ++){
    
    -0.69
    ));
    
    -0.69
    POSITIVE LOGITS
     Python
    0.88
    python
    0.76
     python
    0.75
    Python
    0.74
     Py
    0.73
    elif
    0.73
    Py
    0.71
     py
    0.64
     raise
    0.63
    PYTHON
    0.63
    Activations Density 1.383%

    No Known Activations