© 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. 9-GEMMASCOPE-RES-131K
    11. 35897
    Prev
    Next
    INDEX
    Explanations

    keywords and components related to user interface alerts and dialog boxes in programming

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

    UI dialogs and media types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fancy
    -0.31
    地在
    -0.28
    ToListAsync
    -0.27
     دقت
    -0.26
     fancy
    -0.26
    Pref
    -0.25
     greed
    -0.25
     prop
    -0.24
    PhysRevD
    -0.24
    Fancy
    -0.24
    POSITIVE LOGITS
    SequentialGroup
    1.48
     DialogInterface
    1.38
     DialogResult
    1.27
     UIAlert
    1.27
     JOptionPane
    1.26
     RequestMethod
    1.13
    DialogResult
    1.04
    extAlignment
    0.96
     MediaType
    0.91
    MessageTagHelper
    0.85
    Activations Density 0.001%

    No Known Activations