© 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. 15545
    Prev
    Next
    INDEX
    Explanations

    details related to audio equipment and their functionality

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

    This neuron activates for technical product descriptions related to electronic devices, particularly for audio equipment like headphones, Bluetooth speakers, and wireless technology.

    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
    gather
    -0.32
    idjan
    -0.32
    DebuggerNonUser
    -0.32
     driving
    -0.31
     nấu
    -0.31
     berken
    -0.30
    driving
    -0.30
     gathering
    -0.29
     soil
    -0.29
    ]['
    -0.28
    POSITIVE LOGITS
     Administrativna
    0.65
     earbuds
    0.63
    يكب
    0.62
     ब्रेकडाउन
    0.58
    AsUp
    0.58
    Ecotoxicity
    0.56
    webElementXpaths
    0.55
     AirPods
    0.55
    msgTypes
    0.55
     transférez
    0.54
    Activations Density 0.065%

    No Known Activations