© 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. 106907
    Prev
    Next
    INDEX
    Explanations

    elements related to scientific studies and experiments

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

    stock browser, valence band

    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
    verwijspagina
    -0.62
    BufferException
    -0.59
    setupUi
    -0.50
    المكان
    -0.49
    RegistryLite
    -0.48
    tagHelper
    -0.47
     actionMode
    -0.47
     translateY
    -0.47
    ficulty
    -0.46
    fjspx
    -0.46
    POSITIVE LOGITS
    tegen
    0.41
     réputation
    0.40
     reputación
    0.36
     Komunikasi
    0.35
     Olímpicos
    0.35
     sensibilidad
    0.35
    淹
    0.35
     Española
    0.34
    akses
    0.34
    hány
    0.34
    Activations Density 0.605%

    No Known Activations