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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9580
    Prev
    Next
    INDEX
    Explanations

    key concepts related to healthcare and patient treatment requirements

    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
    følgelig
    -0.66
     OFDb
    -0.66
    []
    
    -0.63
    [];
    
    -0.60
    ()))
    
    -0.59
    )");
    
    -0.59
     ]
    
    -0.59
    Autoritní
    -0.58
    ContentAsync
    -0.56
    [])
    
    -0.55
    POSITIVE LOGITS
     regardless
    2.97
    regardless
    2.67
     irrespective
    2.50
     Regardless
    2.31
    Regardless
    2.25
     even
    2.19
     whether
    2.08
    whether
    1.85
    even
    1.84
    不论
    1.82
    Activations Density 0.991%

    No Known Activations