© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 13282
    Prev
    Next
    INDEX
    Explanations

    the verb "turn" in various contexts and forms, indicating a focus on transformations or changes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    guous
    -0.59
    geschenk
    -0.57
    assies
    -0.56
     gynhyrchwyd
    -0.54
    cys
    -0.54
     Szk
    -0.52
    SIS
    -0.52
     bookId
    -0.52
    Paco
    -0.51
    idios
    -0.51
    POSITIVE LOGITS
     Turn
    1.50
     turn
    1.49
    turn
    1.47
    Turn
    1.45
     TURN
    1.40
    TURN
    1.40
     turned
    1.36
     turning
    1.32
     turns
    1.31
    Turned
    1.30
    Activations Density 0.200%

    No Known Activations