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. 4087
    Prev
    Next
    INDEX
    Explanations

    terms related to null or empty values in programming contexts

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

    Code that assigns/returns/checks for null values

    np_acts-logits-general · gemini-2.0-flash

    null, nil, zero values

    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
    ]));
    
    -0.73
     }));
    -0.71
    ])));
    -0.71
    "}},
    -0.71
    "]))
    -0.71
    "]),
    -0.70
    ())));
    -0.70
    ())),
    -0.69
    ')),
    -0.69
    )));
    
    -0.69
    POSITIVE LOGITS
    :✨
    0.74
    Personensuche
    0.64
     étrangères
    0.61
     obligé
    0.58
     Wikispecies
    0.58
     extérieures
    0.57
     createSprite
    0.54
    apunov
    0.54
     كومونز
    0.53
     Niemand
    0.53
    Activations Density 0.082%

    No Known Activations