© 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. 10-GEMMASCOPE-RES-16K
    11. 5684
    Prev
    Next
    INDEX
    Explanations

    instances of the word "act" and its variations, indicating a focus on actions and agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    󠁢
    -0.48
    databinding
    -0.48
    mány
    -0.43
    criptors
    -0.40
     DIFF
    -0.39
     Aeros
    -0.38
    ستار
    -0.38
     Crom
    -0.38
    getParameter
    -0.37
     Year
    -0.37
    POSITIVE LOGITS
     acting
    0.75
    Acting
    0.70
    行动
    0.67
     agir
    0.67
    acting
    0.65
     Acción
    0.65
    行動
    0.64
     action
    0.64
     acción
    0.63
     Acting
    0.63
    Activations Density 0.361%

    No Known Activations