© 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. 91752
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to scientific processes and effects

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

    temperature dependencies and optimal conditions

    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
     useAppContext
    -0.47
    utilisons
    -0.37
    bleven
    -0.36
    TacToe
    -0.35
     nachdem
    -0.34
    bbi
    -0.32
     dokun
    -0.32
     olympique
    -0.31
     Inject
    -0.31
     jäm
    -0.31
    POSITIVE LOGITS
    تفصیلات
    0.58
     evaporation
    0.56
     optimal
    0.55
     comfort
    0.55
    ьаж
    0.52
     optimum
    0.52
     physiological
    0.50
     performance
    0.50
     solubility
    0.50
     Optimal
    0.50
    Activations Density 0.128%

    No Known Activations