© 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. 20-GEMMASCOPE-RES-16K
    11. 259
    Prev
    Next
    INDEX
    Explanations

    mathematical comparisons and relationships, especially involving values and operations

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

    after conjunctions or punctuation

    np_acts-logits-general · gemini-2.0-flash

    nothingness

    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
     nemlig
    -0.63
    msgTypes
    -0.60
    SequentialGroup
    -0.59
     enää
    -0.59
     geliyor
    -0.58
     prøve
    -0.55
     оригіналу
    -0.55
    enumi
    -0.54
     varandra
    -0.54
    <bos>
    -0.54
    POSITIVE LOGITS
     water
    0.87
     trees
    0.84
     food
    0.79
     eating
    0.78
     shoes
    0.73
     dogs
    0.72
     cars
    0.72
     foods
    0.71
     airplanes
    0.70
     music
    0.70
    Activations Density 0.654%

    No Known Activations