© 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. 15-GEMMASCOPE-RES-16K
    11. 8367
    Prev
    Next
    INDEX
    Explanations

    references to individuals associated with loyalty and conflict during historical periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kuri
    -0.44
    δι
    -0.44
    victory
    -0.43
     succeed
    -0.42
    Success
    -0.41
     edilir
    -0.41
     Ponce
    -0.41
     đa
    -0.41
     Popular
    -0.40
    bilirsiniz
    -0.39
    POSITIVE LOGITS
     participated
    1.01
     participates
    0.99
    Participating
    0.97
     participating
    0.96
     participate
    0.95
     Participating
    0.95
     partici
    0.92
    particip
    0.91
     participation
    0.90
     Participate
    0.81
    Activations Density 0.385%

    No Known Activations