© 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. 66608
    Prev
    Next
    INDEX
    Explanations

    highly activated or emphasized phrases and concepts indicative of importance or significance in the text

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

    names from various fields

    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
    ValueStyle
    -0.63
    PyExc
    -0.55
     AssemblyVersion
    -0.50
     esternos
    -0.49
    Carriera
    -0.48
    fxml
    -0.46
     Soud
    -0.45
    Datuak
    -0.45
    évaluateur
    -0.44
    tvguidetime
    -0.44
    POSITIVE LOGITS
     supérieurs
    0.50
    appui
    0.44
     delà
    0.43
     élevés
    0.41
     bassi
    0.38
    principalTable
    0.38
    qvarna
    0.38
     avoient
    0.37
     rekening
    0.37
     élevé
    0.36
    Activations Density 0.025%

    No Known Activations