© 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. 644
    Prev
    Next
    INDEX
    Explanations

    quotations and questions

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

    phrases centered around questions and reflective prompts

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

    questions and answers

    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
    SourceChecksum
    -0.61
     архивлан
    -0.57
     autorytatywna
    -0.57
     ComVisible
    -0.52
    setVerticalGroup
    -0.51
     يتيمه
    -0.49
    WithIOException
    -0.47
     OMITBAD
    -0.46
    Rüyada
    -0.45
    velocityX
    -0.45
    POSITIVE LOGITS
    Tell
    1.05
    Describe
    0.97
     Tell
    0.97
    Q
    0.94
     Describe
    0.88
     tell
    0.88
    DESCR
    0.85
     TELL
    0.82
     how
    0.78
    describe
    0.76
    Activations Density 0.038%

    No Known Activations