© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 65955
    Prev
    Next
    INDEX
    Explanations

    expressions related to emotional states and feelings

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

    feelings and sensations

    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
     queſta
    -0.67
     مشين
    -0.65
    脚注の使い方
    -0.63
    Tembelea
    -0.62
    MockBean
    -0.61
    qrstuvwxyz
    -0.58
     $_(
    -0.57
    AndEndTag
    -0.56
    TestingModule
    -0.55
    клопе
    -0.55
    POSITIVE LOGITS
     feeling
    1.84
     feelings
    1.55
    feeling
    1.47
     sensación
    1.42
     Feeling
    1.39
     sensação
    1.34
     sensazione
    1.33
     sensation
    1.32
    Feeling
    1.31
     sensations
    1.29
    Activations Density 0.073%

    No Known Activations