© 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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 4244
    Prev
    Next
    INDEX
    Explanations

    terms related to jury trials, fairness, and the legal process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.74
    IVEREF
    -0.64
    참고
    -0.60
    (&:
    -0.57
    .
    -0.55
     malheureusement
    -0.55
     chrétienne
    -0.54
     préalable
    -0.53
     égale
    -0.53
     Surely
    -0.52
    POSITIVE LOGITS
     disambiguazione
    0.85
     zvuky
    0.64
    [])
    
    0.62
     NUKAT
    0.58
     Signalez
    0.54
    MemoryWarning
    0.53
    "))
    
    0.53
     Chwiliwch
    0.52
    aderie
    0.52
    loài
    0.52
    Activations Density 0.831%

    No Known Activations