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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15679
    Prev
    Next
    INDEX
    Explanations

    discussions related to evolutionary biology and the mechanisms of adaptation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsContent
    -0.58
     Fulda
    -0.56
    OSPH
    -0.52
    ImageContext
    -0.50
     ويكيميديا
    -0.50
    titleMargin
    -0.48
     detention
    -0.46
     Pelle
    -0.46
     Asser
    -0.46
     Tiz
    -0.46
    POSITIVE LOGITS
     evolution
    1.73
     evolutionary
    1.72
     evolved
    1.47
    evolution
    1.47
    Evolution
    1.45
     Evolution
    1.39
     evolve
    1.39
     evolu
    1.34
     Evolutionary
    1.32
     EVOLUTION
    1.29
    Activations Density 1.124%

    No Known Activations