© 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. 4-GEMMASCOPE-RES-16K
    11. 10439
    Prev
    Next
    INDEX
    Explanations

    concepts related to causal relationships and independence in statistical models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    væ
    -0.47
     lặng
    -0.47
    JPanel
    -0.45
    Mun
    -0.44
     Ste
    -0.44
     expéri
    -0.43
     kecepatan
    -0.42
     Weeknd
    -0.42
    ACCESS
    -0.41
     Low
    -0.41
    POSITIVE LOGITS
    AutoScaleMode
    0.97
     interdependence
    0.89
    IntoConstraints
    0.88
    mappedBy
    0.81
     disambiguazione
    0.78
     dependencies
    0.77
    TintMode
    0.77
    tonode
    0.76
     synergies
    0.75
    homonymie
    0.74
    Activations Density 2.412%

    No Known Activations