© 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 - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1862
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or terms related to "Shi" entities, likely indicating a focus on a specific topic or field connected to the term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cress
    -0.74
     Corinthians
    -0.71
     Jamb
    -0.69
     Crim
    -0.68
     Haller
    -0.68
    inthians
    -0.67
     Andree
    -0.66
     Kunt
    -0.66
     rex
    -0.66
     Kessler
    -0.64
    POSITIVE LOGITS
     Shi
    3.19
    Shi
    3.02
     shi
    2.71
    shi
    2.42
     Shia
    1.64
     Shields
    1.51
     shifter
    1.45
    SHI
    1.44
     shippers
    1.37
     shipper
    1.36
    Activations Density 0.069%

    No Known Activations