© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 16410
    Prev
    Next
    INDEX
    Explanations

    assertive and definitive statements in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alló
    -0.57
     doigts
    -0.57
     Grecs
    -0.56
     genoux
    -0.56
     répar
    -0.56
     trouvait
    -0.54
     ympä
    -0.54
     vectoriales
    -0.54
     enfans
    -0.53
     déclarations
    -0.53
    POSITIVE LOGITS
     respectively
    1.20
    respectively
    1.07
     respective
    0.88
     alike
    0.86
    両方
    0.84
     both
    0.82
     respectivamente
    0.81
     beiden
    0.78
     Both
    0.78
    どちらも
    0.77
    Activations Density 0.253%

    No Known Activations