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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 9331
    Prev
    Next
    INDEX
    Explanations

    fields and properties in structured data or code

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

    Code-related punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    code, css, json, url, paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -0.80
    </code>
    -0.75
    </strong>
    -0.68
    </b>
    -0.65
    </u>
    -0.62
     »
    -0.60
     });
    -0.59
     ];
    -0.56
     ");
    -0.56
     }),
    -0.55
    POSITIVE LOGITS
    :
    
    1.28
    */
    
    1.23
    ,
    
    1.22
    GEBURTSDATUM
    1.18
    .
    
    1.18
    ).
    
    1.15
    """
    
    1.14
    。
    
    1.14
    ',
    
    1.11
    ?
    
    1.10
    Activations Density 0.243%

    No Known Activations