© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 11117
    Prev
    Next
    INDEX
    Explanations

    references to the term "Hal" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
    hoeddwyd
    -0.57
     noDo
    -0.55
     فريبيس
    -0.55
    reportWebVitals
    -0.53
    IntoConstraints
    -0.50
     nonUne
    -0.50
     Autorizaciones
    -0.48
    ItemBackground
    -0.47
     nakalista
    -0.46
     المعيارى
    -0.46
    POSITIVE LOGITS
     hal
    2.95
     Hal
    2.77
    Hal
    2.75
    hal
    2.70
     HAL
    2.50
    HAL
    2.33
     Halo
    1.59
     halo
    1.59
    halo
    1.58
    Halo
    1.54
    Activations Density 0.970%

    No Known Activations