© 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. 3-GEMMASCOPE-RES-16K
    6. 6854
    Prev
    Next
    INDEX
    Explanations

    function declarations and calls in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MÁ
    -0.67
    vaj
    -0.63
    gok
    -0.62
     Bemer
    -0.60
    ori
    -0.57
     tay
    -0.57
     kiz
    -0.57
    ς
    -0.56
     Ovid
    -0.56
     Ат
    -0.56
    POSITIVE LOGITS
    ✨:
    0.91
    CORBA
    0.87
     disambiguazione
    0.85
     ++)
    0.83
    rillation
    0.81
     nahilalakip
    0.80
    mopol
    0.79
     continúas
    0.78
     nawr
    0.77
    حوالہ
    0.77
    Activations Density 0.275%

    No Known Activations