© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6885
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to software applications and functions

    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
    val
    -0.49
     One
    -0.45
    nO
    -0.44
    One
    -0.44
    യാ
    -0.42
    ματα
    -0.41
    pro
    -0.39
    rat
    -0.39
    nom
    -0.39
    اط
    -0.39
    POSITIVE LOGITS
    setVerticalGroup
    1.01
    الدراسه
    0.90
    новниш
    0.84
    IntoConstraints
    0.80
     AssemblyCulture
    0.80
     Vikipedi
    0.79
    Sklici
    0.78
    featureID
    0.78
    WebVitals
    0.77
    انيف
    0.76
    Activations Density 0.489%

    No Known Activations