© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4398
    Prev
    Next
    INDEX
    Explanations

    words and phrases that involve "wh-" question words or relative pronouns

    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
    adaptiveStyles
    -0.61
     intStringLen
    -0.50
    providedIn
    -0.45
    Kanpo
    -0.45
    Ӕ
    -0.45
    ご
    -0.43
     nahilalakip
    -0.42
    Autoritní
    -0.40
     UITextField
    -0.40
     насељу
    -0.40
    POSITIVE LOGITS
     wh
    1.38
    Wh
    1.30
    wh
    1.25
     Wh
    1.22
     WH
    1.09
    WH
    1.09
    Whit
    1.06
     Whi
    1.02
    Whi
    1.01
     whi
    0.98
    Activations Density 0.568%

    No Known Activations