© 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. 7889
    Prev
    Next
    INDEX
    Explanations

    transitional words and phrases that indicate specific relationships or timeframes in the text

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

    Adverbs that modify a sentence

    np_acts-logits-general · gemini-2.0-flash

    adverbs introducing propositional content

    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
    :✨
    -0.72
    herself
    -0.68
    ſelf
    -0.62
     whofe
    -0.61
    yntaxException
    -0.60
    ſelves
    -0.59
     Houſe
    -0.59
     kasarigan
    -0.57
    oredCriteria
    -0.56
     ddelweddau
    -0.55
    POSITIVE LOGITS
     they
    1.58
     we
    1.56
     it
    1.37
     there
    1.34
     you
    1.12
     he
    0.99
     I
    0.84
     she
    0.83
     они
    0.82
    there
    0.81
    Activations Density 0.278%

    No Known Activations