© 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. 1445
    Prev
    Next
    INDEX
    Explanations

    HTML tags and their attributes

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

    Japanese quotation marks and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Anſ
    -1.45
     itſelf
    -1.38
     Reſ
    -1.31
     Diſ
    -1.27
     Monfieur
    -1.24
     myſelf
    -1.23
     Jefus
    -1.23
     Inſ
    -1.22
     Shakspeare
    -1.20
     himſelf
    -1.19
    POSITIVE LOGITS
     propOrder
    0.88
     van
    0.86
     y
    0.84
     initComponents
    0.83
     da
    0.81
    richTextPanel
    0.81
    MigrationBuilder
    0.79
     co
    0.79
     her
    0.77
     so
    0.76
    Activations Density 0.008%

    No Known Activations