© 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. 36-GEMMASCOPE-RES-16K
    11. 14900
    Prev
    Next
    INDEX
    Explanations

    references to rewards and incentive structures in feedback or research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.38
    SuppressLint
    -0.36
    fitrión
    -0.35
    Capacidad
    -0.33
     filter
    -0.32
     перено
    -0.31
     вме
    -0.30
     Nom
    -0.30
     Lawson
    -0.29
     Normdatei
    -0.29
    POSITIVE LOGITS
     reward
    3.23
     rewards
    3.05
     Reward
    2.73
    reward
    2.64
    Reward
    2.56
     Rewards
    2.56
     rewarded
    2.52
    Rewards
    2.47
    rewards
    2.41
     récompense
    2.34
    Activations Density 0.447%

    No Known Activations