© 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. 13621
    Prev
    Next
    INDEX
    Explanations

    references to boxes and their specifications or properties

    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
    aarrggbb
    -0.84
    PerformLayout
    -0.83
    rslt
    -0.73
    ModelAdmin
    -0.73
    ########.
    -0.71
    FirstResponder
    -0.70
    DSA
    -0.69
    withstanding
    -0.68
    Uli
    -0.68
    اصمة
    -0.68
    POSITIVE LOGITS
     box
    1.90
     boxes
    1.89
     BOX
    1.88
     Box
    1.85
    BOX
    1.72
    box
    1.71
     Boxes
    1.69
    boxes
    1.64
    Box
    1.59
    Boxes
    1.43
    Activations Density 0.110%

    No Known Activations