© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18013
    Prev
    Next
    INDEX
    Explanations

    expressions of enjoyment or fun experiences

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

    having fun

    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
    ModelSerializer
    -0.36
     escaleras
    -0.35
    IntoConstraints
    -0.35
     leyendas
    -0.35
    ########.
    -0.35
     directa
    -0.34
     escase
    -0.32
    tizado
    -0.31
     Fiscalía
    -0.31
     affid
    -0.31
    POSITIVE LOGITS
     enjoyment
    0.86
     ENJOY
    0.84
     Spaß
    0.78
     fun
    0.77
    enjoy
    0.76
     divertimento
    0.74
     divertir
    0.72
     enjoyable
    0.72
     Enjoy
    0.71
     весе
    0.69
    Activations Density 0.084%

    No Known Activations