© 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. 20-GEMMASCOPE-RES-131K
    6. 124384
    Prev
    Next
    INDEX
    Explanations

    terms related to biological signaling pathways and protein interactions

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

    STAT complex formation and translocation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.69
     المعيارى
    -0.58
    RegressionTest
    -0.57
    tiness
    -0.52
    Fordítás
    -0.51
    RTSN
    -0.50
     betweenstory
    -0.50
    stylers
    -0.50
    EDEFAULT
    -0.50
     NSCoder
    -0.50
    POSITIVE LOGITS
    yarnpkg
    0.42
     comuniques
    0.35
     generally
    0.33
     informée
    0.33
    '][$
    0.32
     typically
    0.30
    ExecuteReader
    0.30
    ónimos
    0.29
     cherchés
    0.29
     usually
    0.28
    Activations Density 0.149%

    No Known Activations