© 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. 60623
    Prev
    Next
    INDEX
    Explanations

    important structural elements in a document, particularly relating to first identifiers and numeric values

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

    names, numbers, and legal text

    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
    Personendaten
    -0.65
     doInBackground
    -0.61
    windowFixed
    -0.56
     Roskov
    -0.52
     EconPapers
    -0.50
    BagLayout
    -0.50
     gravedad
    -0.49
    thâu
    -0.49
    interopRequire
    -0.48
    lccn
    -0.47
    POSITIVE LOGITS
    +:+
    0.37
     оригіналу
    0.36
    胎
    0.32
     tuviera
    0.31
    AutoField
    0.31
    étrie
    0.30
     habría
    0.29
     īpa
    0.29
    acter
    0.29
    出
    0.28
    Activations Density 0.252%

    No Known Activations