© 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. 90344
    Prev
    Next
    INDEX
    Explanations

    terms related to autophagy and its role in metabolic processes and immune response

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

    autophagy and phagocytic processes

    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
     initComponents
    -0.43
    ModelAttribute
    -0.39
     sols
    -0.35
     hir
    -0.34
     Numerade
    -0.34
     rút
    -0.34
     embarazo
    -0.33
     borrowing
    -0.33
     mantequilla
    -0.33
    initializeApp
    -0.33
    POSITIVE LOGITS
     autophagy
    0.91
     Autop
    0.82
     autop
    0.77
    autop
    0.69
    opha
    0.57
    hagy
    0.54
    hagic
    0.51
    IntoConstraints
    0.49
    tosis
    0.49
    verwijspagina
    0.48
    Activations Density 0.190%

    No Known Activations