© 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. 564
    Prev
    Next
    INDEX
    Explanations

    elements related to licensing and legal terms

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

    references to scriptural passages or authoritative religious texts

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

    license and associated legal text

    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
     Efq
    -0.73
     étoit
    -0.71
    PerformLayout
    -0.70
     pouvoit
    -0.68
     Nacionales
    -0.68
     avoient
    -0.68
     leaſt
    -0.68
     auroit
    -0.68
     feroit
    -0.67
    kloped
    -0.66
    POSITIVE LOGITS
     cabe
    0.47
    thys
    0.47
    rometry
    0.46
    BuildContext
    0.45
    dite
    0.45
    ABUL
    0.45
    hoek
    0.44
     pare
    0.43
    omyces
    0.42
    nan
    0.41
    Activations Density 0.060%

    No Known Activations