© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 687
    Prev
    Next
    INDEX
    Explanations

    phrases related to official reports and announcements

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

    discussions around energy costs and efficiency

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

    commenting on names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ^(@)
    -0.86
     beginnetje
    -0.86
    IsContent
    -0.82
    LEncoder
    -0.81
     estekak
    -0.78
    PyExc
    -0.73
     Мексичка
    -0.72
    Pratique
    -0.71
     BorderSide
    -0.70
     HttpNotFound
    -0.69
    POSITIVE LOGITS
    Commenting
    0.56
     Professor
    0.56
     Comment
    0.55
     today
    0.53
     comments
    0.52
     Baroness
    0.52
    Professor
    0.51
     Ahead
    0.50
    Comment
    0.50
    Ahead
    0.48
    Activations Density 0.069%

    No Known Activations