© 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 EvalsExportsinterp-engineNEWAPI 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. 45063
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and symptoms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Center
    -0.44
     Center
    -0.42
    centered
    -0.37
     nakalista
    -0.35
     Centers
    -0.34
    Neighbor
    -0.34
     пови
    -0.34
     center
    -0.34
    woff
    -0.33
     Flavor
    -0.32
    POSITIVE LOGITS
     behavioural
    0.95
     generalised
    0.94
     coloured
    0.90
    setVerticalGroup
    0.88
     behaviour
    0.87
     tumour
    0.86
     Behavioural
    0.86
     Initialise
    0.84
     learnt
    0.83
     colours
    0.82
    Activations Density 0.508%

    No Known Activations