© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 123943
    Prev
    Next
    INDEX
    Explanations

    file types and extensions related to web development frameworks and languages

    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
    Tikang
    -0.61
     utafitiHapana
    -0.59
    脚注の使い方
    -0.55
     nonUne
    -0.52
    RenderAtEndOf
    -0.50
    LLocation
    -0.50
    openConnection
    -0.50
    orteur
    -0.49
    Transfer
    -0.49
    Kariera
    -0.49
    POSITIVE LOGITS
    ejs
    1.66
    hbs
    0.94
    handlebars
    0.77
     TMPro
    0.51
    ViewFeatures
    0.51
     modelAndView
    0.48
    ⟬
    0.46
    YSQL
    0.44
    BagLayout
    0.42
    IntoConstraints
    0.42
    Activations Density 0.001%

    No Known Activations