© 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. 1400
    Prev
    Next
    INDEX
    Explanations

    specific categories and classifications related to individuals and organizations

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

    categories of people and locations related to specific entities

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

    categorizing birth years

    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
    +#+#
    -0.72
    IntoConstraints
    -0.67
     LUMP
    -0.67
    seteq
    -0.61
     TableColumn
    -0.59
    issauga
    -0.57
     Majefty
    -0.57
     teens
    -0.56
    Drupal
    -0.56
    Tikang
    -0.56
    POSITIVE LOGITS
     born
    2.38
     birth
    2.37
     Born
    1.96
    birth
    1.95
    Born
    1.88
    born
    1.86
     Birth
    1.85
    Birth
    1.81
     BORN
    1.75
     naissance
    1.70
    Activations Density 0.270%

    No Known Activations