© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 2996
    Prev
    Next
    INDEX
    Explanations

    the word "what" in various contexts and its combinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    How
    -0.48
     How
    -0.45
    genomen
    -0.42
    Which
    -0.41
     portanto
    -0.36
     лов
    -0.36
     grounds
    -0.35
     Which
    -0.35
    进制
    -0.35
    cí
    -0.34
    POSITIVE LOGITS
     what
    1.27
     propOrder
    0.83
    PreExecute
    0.69
    Personendaten
    0.66
     everything
    0.65
    ніципалі
    0.65
     quello
    0.63
    ModelSerializer
    0.62
    Obrázky
    0.61
    quilo
    0.60
    Activations Density 0.104%

    No Known Activations