© 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. 5483
    Prev
    Next
    INDEX
    Explanations

    instances of coordination and conjunction in sentences

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

    Text following "Q:" (likely questions)

    np_acts-logits-general · gemini-2.0-flash

    programming and technical terms

    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
     createState
    -0.78
     amelyek
    -0.59
     rechange
    -0.55
     hanem
    -0.52
     légiti
    -0.49
    Panamoan
    -0.49
    ыгана
    -0.47
     negativas
    -0.47
     verticales
    -0.46
     hlavně
    -0.46
    POSITIVE LOGITS
    WebVitals
    0.92
    semantics
    0.69
    alamus
    0.65
    onViewCreated
    0.63
     surla
    0.62
     pinulongan
    0.61
    NamedQueries
    0.61
     trusts
    0.60
     coaching
    0.59
    swire
    0.59
    Activations Density 0.505%

    No Known Activations