Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12352
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references in formal documents

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

    Follows punctuation or new lines

    np_acts-logits-general · gemini-2.0-flash

    legal filings involving madness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    phosa
    -0.30
    Viel
    -0.26
    ıll
    -0.25
     Вікі
    -0.25
     poussière
    -0.24
    switch
    -0.24
     Viel
    -0.23
     encima
    -0.23
     Vereinbarung
    -0.23
     מל
    -0.23
    POSITIVE LOGITS
     lunatic
    0.73
     AssemblyCompany
    0.73
     kasarigan
    0.71
     betweenstory
    0.66
     folle
    0.64
     eccentric
    0.63
     Wiktionnaire
    0.63
     madman
    0.63
     madness
    0.62
    verifyException
    0.62
    Activations Density 0.478%

    No Known Activations