© 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. 64183
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional states and feelings

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

    feelings about

    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
    WithIOException
    -0.67
     للمعارف
    -0.65
     AssemblyCompany
    -0.63
     HasFactory
    -0.63
    InputBorder
    -0.60
    ValueGeneration
    -0.60
    OGND
    -0.53
    awtextra
    -0.52
     hogyan
    -0.52
     AppCompatTheme
    -0.50
    POSITIVE LOGITS
     about
    1.09
    about
    0.66
     About
    0.57
    About
    0.57
     ABOUT
    0.56
     tentang
    0.56
     tungkol
    0.53
     abou
    0.45
    bout
    0.44
     humiliated
    0.43
    Activations Density 0.013%

    No Known Activations