© 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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10726
    Prev
    Next
    INDEX
    Explanations

    technical terms and function-related keywords in programming code

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

    GUI or GTK-related code

    np_acts-logits-general · gemini-2.0-flash

    GTK UI elements and functions

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     initComponents
    -0.88
    DockStyle
    -0.74
    endregion
    -0.68
    ChildScrollView
    -0.60
    setVerticalGroup
    -0.53
     CreateTagHelper
    -0.53
    IntoConstraints
    -0.52
     Infórmanos
    -0.51
    GroupLayout
    -0.51
    initComponents
    -0.50
    POSITIVE LOGITS
     nahilalakip
    0.53
    Personendaten
    0.49
    sidemargin
    0.47
     EconPapers
    0.39
    Tembelea
    0.38
    CppMethod
    0.37
     perpetuity
    0.35
    opération
    0.35
    adesivo
    0.34
     miniaturka
    0.34
    Activations Density 0.457%

    No Known Activations