© 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. 5-GEMMASCOPE-RES-16K
    11. 9310
    Prev
    Next
    INDEX
    Explanations

    interrogative words, particularly questions starting with "What."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    numerusform
    -0.90
    ؤلاء
    -0.81
    ChildScrollView
    -0.81
    expandindo
    -0.81
    couvrez
    -0.80
    XmlAccessorType
    -0.74
     صوتيه
    -0.74
    NameInMap
    -0.74
     validamos
    -0.73
    Polecam
    -0.73
    POSITIVE LOGITS
    What
    1.70
     What
    1.67
    what
    1.24
    WHAT
    1.21
    How
    1.20
     WHAT
    1.17
     How
    1.14
     what
    1.11
    Why
    1.02
     Why
    0.96
    Activations Density 0.101%

    No Known Activations