© 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. 20-GEMMASCOPE-RES-131K
    11. 113422
    Prev
    Next
    INDEX
    Explanations

    references to scientific research and methodologies, particularly in medical and technical contexts

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

    ink stains, transient neuronal, likes seeing, axisymmetric

    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
     चीज़ों
    -0.42
    historie
    -0.39
     prová
    -0.36
     cap
    -0.35
     glorified
    -0.35
    endpush
    -0.35
    ecap
    -0.35
    outState
    -0.35
     schön
    -0.34
    ◄
    -0.34
    POSITIVE LOGITS
    rungsseite
    0.65
     propOrder
    0.50
    MigrationBuilder
    0.50
    abestanden
    0.48
    ußt
    0.47
    httphttps
    0.47
     يتيمه
    0.46
    UnsafeEnabled
    0.45
     EconPapers
    0.45
     AssemblyTitle
    0.42
    Activations Density 0.186%

    No Known Activations