© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 23719
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement and anticipation related to events or activities

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

    excitement and anticipation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addCriterion
    -0.42
     insult
    -0.41
    FailureListener
    -0.37
     ویکی‌پدیا
    -0.37
     poveznice
    -0.36
     disagreeable
    -0.34
    diak
    -0.32
    EndContext
    -0.32
    ndef
    -0.32
    uis
    -0.32
    POSITIVE LOGITS
     excitement
    2.30
     excited
    2.08
     Excited
    1.84
    Excited
    1.84
     excite
    1.81
     excitedly
    1.81
    excited
    1.79
     excites
    1.66
     exciting
    1.56
     excitation
    1.45
    Activations Density 0.171%

    No Known Activations