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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30208
    Prev
    Next
    INDEX
    Explanations

    phrases that involve asking someone for assistance or information

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

    you want or are interested

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     consultato
    -0.96
    MLLoader
    -0.88
     للمعارف
    -0.84
     utafitiHapana
    -0.79
    клопе
    -0.79
    DockStyle
    -0.79
     propOrder
    -0.78
    下载附件
    -0.73
    XmlAccessorType
    -0.73
    AccessorTable
    -0.72
    POSITIVE LOGITS
     interested
    0.56
     createState
    0.52
     want
    0.47
    Interested
    0.42
     Interested
    0.42
    ṃ
    0.41
    nolia
    0.41
     интересу
    0.41
     Want
    0.40
    esis
    0.40
    Activations Density 0.036%

    No Known Activations