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. 13771
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking instructions in recipes

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

    Food preparation: slicing, chopping, shaving

    np_acts-logits-general · gemini-2.0-flash

    food preparation shapes

    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
     تانيه
    -0.60
    imenta
    -0.47
     کیلوم
    -0.46
     nahilalakip
    -0.44
    WriteBarrier
    -0.43
     gynnwys
    -0.43
    tagHelperRunner
    -0.42
    ImageContext
    -0.42
     mustard
    -0.41
     consenti
    -0.41
    POSITIVE LOGITS
     slices
    0.96
     strips
    0.93
     sliced
    0.89
     slice
    0.82
     cubes
    0.82
     potongan
    0.80
     strip
    0.79
     chunks
    0.77
     Strips
    0.75
     cubed
    0.74
    Activations Density 0.290%

    No Known Activations