© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7519
    Prev
    Next
    INDEX
    Explanations

    instances of the word "two" or its variants and their contextual significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    IconModule
    -0.59
     Grüsse
    -0.53
    ly
    -0.52
     esercit
    -0.48
     Oberfläche
    -0.47
     atividade
    -0.47
    hláš
    -0.46
    sphase
    -0.46
     Reactivity
    -0.45
    ivity
    -0.45
    POSITIVE LOGITS
     two
    0.99
     three
    0.86
     TWO
    0.76
     four
    0.76
     five
    0.74
     Two
    0.73
     THREE
    0.71
    Two
    0.71
    three
    0.71
    two
    0.67
    Activations Density 0.175%

    No Known Activations