Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13867
    Prev
    Next
    INDEX
    Explanations

    references to textiles and fabric designs associated with various products

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

    "Cute" or visually appealing designs/patterns

    np_acts-logits-general · gemini-2.0-flash

    cute patterns and designs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.91
    AddTagHelper
    -0.91
    SharedDtor
    -0.78
     дописавши
    -0.76
    تقاوى
    -0.69
    ValueStyle
    -0.67
    nologue
    -0.64
     estekak
    -0.64
     @"/
    -0.62
    WriteBarrier
    -0.61
    POSITIVE LOGITS
     patterns
    1.35
     designs
    1.28
     pattern
    1.19
     design
    1.10
     motifs
    1.08
     Patterns
    1.05
    designs
    1.01
    pattern
    1.01
     diseños
    1.01
     patterning
    1.00
    Activations Density 0.185%

    No Known Activations