© 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. 1552
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize inclusion or collective identity

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

    phrases expressing sudden changes or occurrences

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

    all of the

    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
     незавершена
    -0.86
     Signalez
    -0.82
     NSCoder
    -0.82
     &___
    -0.82
     betweenstory
    -0.82
     auffi
    -0.81
     Monfieur
    -0.81
     iſt
    -0.80
     pleaſure
    -0.79
     myſelf
    -0.79
    POSITIVE LOGITS
     sudden
    0.75
     Sudden
    0.51
    sud
    0.49
     surprised
    0.48
    ReusableCell
    0.45
    исленность
    0.44
    Sudden
    0.42
     '\\;'
    0.41
    TableModel
    0.41
     überrascht
    0.39
    Activations Density 0.038%

    No Known Activations