© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 126732
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to pleasantness and enjoyable experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    pleasant qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.56
     cancha
    -0.51
     ihtiyac
    -0.48
     orphan
    -0.48
     corda
    -0.47
     döv
    -0.47
     orphanage
    -0.47
     almacén
    -0.47
     hospitales
    -0.46
     industriels
    -0.46
    POSITIVE LOGITS
     pleasant
    1.29
    pleasant
    1.18
    Pleasant
    1.10
     angene
    1.03
     agradable
    1.03
     Pleasant
    1.03
     прият
    1.01
     agréable
    0.99
     agradável
    0.97
     piacevole
    0.96
    Activations Density 0.008%

    No Known Activations