© 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. 93077
    Prev
    Next
    INDEX
    Explanations

    references to chemical compounds and their properties

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

    adhesive penetration into solid substrates

    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
     mand
    -0.59
     MAND
    -0.56
     mandate
    -0.55
     mandatory
    -0.54
     Mand
    -0.53
     requiring
    -0.53
    Mand
    -0.51
     requirement
    -0.50
     mandated
    -0.48
     mandates
    -0.47
    POSITIVE LOGITS
    Personendaten
    0.65
     незавершена
    0.58
    matchCondition
    0.58
     AssemblyTitle
    0.57
    ----</
    0.56
    ReusableCell
    0.56
    fromnode
    0.53
     AssemblyCompany
    0.53
     MotionEvent
    0.51
    ACHUSET
    0.50
    Activations Density 0.014%

    No Known Activations