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. 16-GEMMASCOPE-RES-16K
    6. 16003
    Prev
    Next
    INDEX
    Explanations

    descriptions of kitchens and their features

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

    the word "kitchen"

    np_acts-logits-general · gemini-2.0-flash

    kitchen and other rooms

    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
     Normdatei
    -0.63
    LLocation
    -0.60
     AppModule
    -0.58
     móds
    -0.54
     adulti
    -0.53
     llegaron
    -0.51
    Distribuzione
    -0.50
     llegó
    -0.50
    asticity
    -0.50
    PreInfinity
    -0.49
    POSITIVE LOGITS
     kitchen
    0.86
     Kitchen
    0.78
    kitchen
    0.72
    Kitchen
    0.69
     kitchenette
    0.69
     chef
    0.67
    migrationBuilder
    0.66
     nakalista
    0.66
     bancada
    0.66
     cooking
    0.65
    Activations Density 0.030%

    No Known Activations