© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5441
    Prev
    Next
    INDEX
    Explanations

    content related to legal processes and outcomes

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

    Numbers following "to", "and", "by", or "below"

    np_acts-logits-general · gemini-2.0-flash

    numbers and number phrases

    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
     &
    -0.71
     
    -0.66
    <bos>
    -0.62
     Govt
    -0.59
     ppl
    -0.55
     govt
    -0.54
    <&
    -0.53
     refugi
    -0.50
     Assn
    -0.49
     enamorado
    -0.48
    POSITIVE LOGITS
     four
    1.35
     five
    1.34
     twenty
    1.33
     six
    1.30
     seven
    1.29
     eight
    1.28
     three
    1.28
     nine
    1.28
     twelve
    1.28
     eighteen
    1.27
    Activations Density 0.269%

    No Known Activations