© 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. 16-GEMMASCOPE-RES-16K
    11. 1797
    Prev
    Next
    INDEX
    Explanations

    references to boxes or similar container-like structures

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

    "box" or its plurals

    np_acts-logits-general · gemini-2.0-flash

    box and boxes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    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
    -0.79
    ########.
    -0.75
    rslt
    -0.69
     Ciri
    -0.69
    StreamReader
    -0.68
     pleaſure
    -0.67
    Uli
    -0.67
    withstanding
    -0.67
    DSA
    -0.66
     DSA
    -0.66
    POSITIVE LOGITS
     boxes
    1.83
     box
    1.81
     BOX
    1.79
     Box
    1.78
     Boxes
    1.63
    BOX
    1.60
    box
    1.59
    boxes
    1.56
    Box
    1.51
    Boxes
    1.42
    Activations Density 0.102%

    No Known Activations