© 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. 31-GEMMASCOPE-RES-16K
    6. 10728
    Prev
    Next
    INDEX
    Explanations

    phrases and instances of listening and communication

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

    phrases where someone actively listens to or pays attention to other people's words or concerns.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.47
     Bewußt
    -0.40
    ivat
    -0.40
    orianCalendar
    -0.39
    quiler
    -0.39
    medriver
    -0.36
    眦
    -0.34
    verwijspagina
    -0.33
    recated
    -0.32
    kheim
    -0.32
    POSITIVE LOGITS
     listening
    2.97
     listen
    2.95
     listened
    2.83
     listens
    2.73
     Listen
    2.64
     Listening
    2.53
    Listen
    2.47
    listen
    2.42
    Listening
    2.36
     LISTEN
    2.36
    Activations Density 0.372%

    No Known Activations