© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1870
    Prev
    Next
    INDEX
    Explanations

    instances of the term "box" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "box" followed by a property or measurement

    np_acts-logits-general · gemini-2.0-flash

    box followed by dimensions or compound words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.66
    migrationBuilder
    -0.65
    ModelAdmin
    -0.63
    DSA
    -0.63
    RegistryLite
    -0.63
    TagHelper
    -0.61
    modelBuilder
    -0.60
    rence
    -0.60
    Uli
    -0.60
    ########.
    -0.59
    POSITIVE LOGITS
     boxes
    1.51
     box
    1.48
     BOX
    1.44
     Box
    1.40
     Boxes
    1.38
    BOX
    1.19
    boxes
    1.17
    Box
    1.16
    box
    1.15
    Boxes
    1.14
    Activations Density 0.070%

    No Known Activations