© 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
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8495
    Prev
    Next
    INDEX
    Explanations

    elements related to software development and UI layout configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ParallelGroup
    -0.63
    ⓧ
    -0.61
     utafitiHapana
    -0.58
    astéroïdes
    -0.56
    ſſung
    -0.55
    addPreferredGap
    -0.55
    ementara
    -0.55
    ſelben
    -0.54
    <unused23>
    -0.53
    <unused71>
    -0.53
    POSITIVE LOGITS
    ResumeLayout
    1.32
    EndInit
    1.23
    BeginInit
    1.05
    SuspendLayout
    0.75
    AutoScale
    0.60
    PerformLayout
    0.60
     initComponents
    0.59
    ClientSize
    0.45
    setVerticalGroup
    0.44
    OGND
    0.44
    Activations Density 0.028%

    No Known Activations