© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 4043
    Prev
    Next
    INDEX
    Explanations

    instances of the word "who" and related wh- words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -1.02
    日閲覧
    -0.98
    دانشنامهٔ
    -0.94
     }}"></
    -0.91
    ();*/
    -0.90
     Ebert
    -0.89
    .*/
    -0.89
     Garnet
    -0.85
    </em>
    -0.85
    *************/
    -0.85
    POSITIVE LOGITS
     Wh
    1.47
    Wh
    1.45
     wh
    1.43
     WH
    1.35
    wh
    1.34
     Wharton
    1.22
    WH
    1.16
     Whiting
    1.16
     Whal
    1.04
     whales
    0.99
    Activations Density 0.014%

    No Known Activations