© 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. 12-GEMMASCOPE-RES-16K
    11. 15065
    Prev
    Next
    INDEX
    Explanations

    references to boxes and their attributes in defined structures or layouts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    withstanding
    -0.90
     pleaſure
    -0.86
    aarrggbb
    -0.85
    PerformLayout
    -0.85
    ModelAdmin
    -0.84
    DSA
    -0.81
     Ciri
    -0.75
     scuro
    -0.74
    */),
    -0.73
    rslt
    -0.73
    POSITIVE LOGITS
     BOX
    1.99
     Box
    1.97
     box
    1.95
     boxes
    1.90
    BOX
    1.79
    box
    1.78
     Boxes
    1.73
    Box
    1.70
    boxes
    1.61
    Boxes
    1.47
    Activations Density 0.048%

    No Known Activations