© 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. 2562
    Prev
    Next
    INDEX
    Explanations

    references to illegal drugs and their distribution

    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
     فريبيس
    -0.88
     Roskov
    -0.82
     propOrder
    -0.73
     مرئيه
    -0.71
    principalTable
    -0.71
     actionMode
    -0.68
    AddTagHelper
    -0.68
    InjectAttribute
    -0.65
     MainAxisSize
    -0.65
    省市镇
    -0.64
    POSITIVE LOGITS
     copies
    0.68
     items
    0.63
     duplicates
    0.54
    copies
    0.54
    copy
    0.54
    Copies
    0.52
     copy
    0.52
     assorted
    0.52
     priced
    0.50
     copie
    0.50
    Activations Density 0.319%

    No Known Activations