© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 90660
    Prev
    Next
    INDEX
    Explanations

    references to grease and lubrication

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

    grease and lard

    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
     resourceCulture
    -0.43
     burbuja
    -0.41
    Rhestr
    -0.39
     graduación
    -0.39
     alfombra
    -0.38
    middels
    -0.38
    drinks
    -0.38
     Pesquisa
    -0.38
     boire
    -0.38
     botella
    -0.37
    POSITIVE LOGITS
     soap
    0.72
     lard
    0.66
     Soap
    0.64
    rungsseite
    0.63
     sapon
    0.62
     graisse
    0.60
    soap
    0.57
     Lard
    0.57
     fatty
    0.57
     candles
    0.56
    Activations Density 0.038%

    No Known Activations