© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-131K
    11. 71486
    Prev
    Next
    INDEX
    Explanations

    references to various types of hormone receptors and their expressions in biological contexts

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

    biological receptors and ligands

    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
    apnews
    -0.49
    OCCURRED
    -0.48
     alinea
    -0.46
    zusammen
    -0.46
     supplies
    -0.44
    
    -0.43
     Offisielt
    -0.43
    windowFixed
    -0.42
     contributions
    -0.42
    strokeStyle
    -0.42
    POSITIVE LOGITS
     receptor
    1.09
     Receptor
    0.95
     receptors
    0.93
     Receptors
    0.91
    receptor
    0.90
     recepto
    0.76
    ceptor
    0.66
    ceptors
    0.56
     receiver
    0.55
     recept
    0.50
    Activations Density 0.129%

    No Known Activations