© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1761
    Prev
    Next
    INDEX
    Explanations

    the name "Saravan" and its variations in different contexts

    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
    ChildScrollView
    -0.88
     cruze
    -0.78
    OGND
    -0.75
    tığı
    -0.73
     cromo
    -0.72
    Eden
    -0.70
    Rodney
    -0.69
     Rodney
    -0.69
    وردار
    -0.66
     oliver
    -0.66
    POSITIVE LOGITS
     Sar
    1.19
    Sar
    1.15
     sar
    1.12
     Vak
    0.88
     Sarasota
    0.86
     Sarac
    0.85
     Cien
    0.83
     Sart
    0.81
     Mennon
    0.81
    onsense
    0.80
    Activations Density 1.202%

    No Known Activations