© 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. 37694
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to cell behavior, migration, and complex interactions in biological contexts

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

    migration of cells

    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
     nozze
    -0.33
    Rhestr
    -0.31
     defStyle
    -0.29
    CardBody
    -0.28
    didSet
    -0.28
    ReusableCell
    -0.28
    icordia
    -0.28
    nodoc
    -0.27
     Numerade
    -0.27
    ïque
    -0.27
    POSITIVE LOGITS
     travelling
    1.81
     traveling
    1.78
     travels
    1.71
     travelled
    1.66
     travel
    1.63
     traveled
    1.60
     Travelling
    1.58
     Traveling
    1.56
    Traveling
    1.53
    traveling
    1.52
    Activations Density 0.582%

    No Known Activations