© 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. 22-GEMMASCOPE-RES-16K
    6. 9204
    Prev
    Next
    INDEX
    Explanations

    instances of structured data or code elements

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

    Code snippets (often C++)

    np_acts-logits-general · gemini-2.0-flash

    closing braces or ends of code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "])
    
    -0.87
    "];
    
    -0.85
    '));
    
    -0.82
    "));
    
    -0.82
    ']);
    
    -0.81
    '];
    
    -0.79
    "]);
    
    -0.79
    '],
    
    -0.74
    '])
    
    -0.72
    ")));
    
    -0.72
    POSITIVE LOGITS
    }
    0.73
     mariée
    0.60
    </tr>
    0.59
    YMMV
    0.58
    poptosis
    0.57
    Демографія
    0.56
    orsese
    0.55
     viata
    0.55
     deschis
    0.54
    };
    0.54
    Activations Density 0.083%

    No Known Activations