© 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. 31-GEMMASCOPE-RES-16K
    11. 2983
    Prev
    Next
    INDEX
    Explanations

    instances of players being discussed in terms of their effectiveness in a specific position

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    specific player names and their performance statistics or playing positions in sports commentary.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     AttributeSet
    -0.68
    elemField
    -0.63
     EconPapers
    -0.58
     nonUne
    -0.54
    UnitTesting
    -0.53
    istoitu
    -0.52
     StatelessWidget
    -0.52
     déf
    -0.51
     Extern
    -0.51
     mergeFrom
    -0.51
    POSITIVE LOGITS
     midfield
    0.85
     midfielder
    0.63
     middle
    0.60
     zentral
    0.50
    middle
    0.49
     mid
    0.49
     central
    0.47
    กลาง
    0.46
     Middle
    0.45
     MIDDLE
    0.44
    Activations Density 0.066%

    No Known Activations