© 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. 20-GEMMASCOPE-RES-16K
    6. 14973
    Prev
    Next
    INDEX
    Explanations

    features and functionalities of touchscreens and digital controls in vehicles

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

    physical control interfaces like buttons, levers, switches, touchscreens, and steering wheel components.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    AddTagHelper
    -0.61
    DBNull
    -0.55
    localctx
    -0.54
    RegressionTest
    -0.53
     kasarigan
    -0.52
    mybatisplus
    -0.50
    mobileqq
    -0.50
    艋
    -0.50
    execSQL
    -0.49
    UnitTesting
    -0.49
    POSITIVE LOGITS
     buttons
    0.48
    CloseOperation
    0.47
     bedien
    0.42
     onOptions
    0.42
     button
    0.42
     command
    0.40
     keypad
    0.39
     controls
    0.38
     управления
    0.38
     touchscreen
    0.37
    Activations Density 0.196%

    No Known Activations