© 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. 91672
    Prev
    Next
    INDEX
    Explanations

    terms related to food preservation and temperature regulation

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

    freezing and cold temperatures

    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
     копия
    -0.34
     irmã
    -0.33
     filha
    -0.33
     originales
    -0.32
    ærer
    -0.31
     Reim
    -0.30
     sáb
    -0.30
    noisy
    -0.29
     Ellis
    -0.29
     lancé
    -0.29
    POSITIVE LOGITS
    rungsseite
    0.64
    хьтан
    0.64
    WebServlet
    0.60
    凍
    0.60
    AddTagHelper
    0.60
     pipes
    0.58
    Geplaatst
    0.58
    ///</
    0.58
     Roskov
    0.57
     ſind
    0.56
    Activations Density 0.013%

    No Known Activations