© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 15164
    Prev
    Next
    INDEX
    Explanations

    terms related to long-term balancing selection in evolutionary genetics

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

    Evolution or selection processes

    np_acts-logits-general · gemini-2.0-flash

    recent evolutionary selection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     personnelle
    -0.61
     tiks
    -0.54
     castello
    -0.48
     McAllister
    -0.48
     Consultative
    -0.48
     crisp
    -0.47
     auprès
    -0.47
     hinaus
    -0.46
     booked
    -0.45
    peak
    -0.45
    POSITIVE LOGITS
    المناصب
    0.83
    олові
    0.80
     evolution
    0.76
    RegressionTest
    0.71
     evolutionary
    0.71
    aptation
    0.70
     ujednoznacz
    0.70
    evolution
    0.65
     evolve
    0.64
    
    0.63
    Activations Density 0.957%

    No Known Activations