© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14549
    Prev
    Next
    INDEX
    Explanations

    references to technology and connectivity features in products

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

    references to electronic connections and cables, particularly USB, connecting devices, and hardware interfaces.

    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
    Referències
    -0.35
    stackoverflow
    -0.33
    lua
    -0.33
    béco
    -0.32
     count
    -0.32
    swatch
    -0.32
    flake
    -0.31
    関
    -0.31
    epam
    -0.31
    SequentialGroup
    -0.30
    POSITIVE LOGITS
     plugged
    0.68
     USB
    0.65
     ब्रेकडाउन
    0.65
     HDMI
    0.64
    Хьажоргаш
    0.63
     cables
    0.60
     usb
    0.60
    :✨
    0.57
     dongle
    0.57
     peripherals
    0.56
    Activations Density 0.181%

    No Known Activations