© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 4505
    Prev
    Next
    INDEX
    Explanations

    instances of the word "combine" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    homonymie
    -0.52
    measure
    -0.50
    Palmarès
    -0.50
    hamilan
    -0.49
    脚注
    -0.46
     medida
    -0.46
     calculées
    -0.45
    vám
    -0.45
     Feier
    -0.45
     vold
    -0.45
    POSITIVE LOGITS
     combine
    0.71
     Combine
    0.70
     combines
    0.63
    Combine
    0.60
    combine
    0.56
     COMBIN
    0.55
    parsedMessage
    0.54
     combin
    0.53
     common
    0.52
     Combined
    0.52
    Activations Density 0.190%

    No Known Activations