© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5699
    Prev
    Next
    INDEX
    Explanations

    references to significant historical events or milestones

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

    proper nouns and specific technical details related to historical or geographical contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    references to named entities and formal factual details—proper nouns, dates, rankings, titles, organizations, places, and historical events common in encyclopedic or news-style text.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    historical references with specific dates, names, and events, particularly in formal or encyclopedic text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     doInBackground
    -0.37
     препратки
    -0.34
    身
    -0.34
    #+#
    -0.34
     sud
    -0.34
    蹶
    -0.32
    突
    -0.32
     AssemblyProduct
    -0.32
     AssemblyCompany
    -0.32
     ог
    -0.32
    POSITIVE LOGITS
     postwar
    0.64
    Sklici
    0.61
     yıllar
    0.61
     насељу
    0.60
     ddelweddau
    0.59
     década
    0.58
    Personensuche
    0.56
     vroeger
    0.56
    IntoConstraints
    0.55
     damals
    0.54
    Activations Density 1.030%

    No Known Activations