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. 7585
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and their measurements, as well as references to legal and contractual language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    </h4>
    -0.59
    rungsseite
    -0.54
    </blockquote>
    -0.49
     "";
    
    -0.47
    AndroidJUnit
    -0.46
     "";
    -0.45
    Filmografia
    -0.44
     '/';
    -0.43
     lateinit
    -0.41
    Referències
    -0.40
    POSITIVE LOGITS
    ).
    2.21
    )
    2.13
    .)
    2.03
    ),
    1.94
    )
    1.92
    ?)
    1.91
    !)
    1.89
    ?).
    1.88
    );
    1.87
    ...)
    1.86
    Activations Density 8.678%

    No Known Activations