© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 12334
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to professional communication and etiquette

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

    modes of communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ब्रेकडाउन
    -0.51
    LookAnd
    -0.47
    ThemeOverlay
    -0.41
    SuspendLayout
    -0.36
    poss
    -0.35
    رشف
    -0.35
     AssemblyCulture
    -0.35
    AISSEE
    -0.34
     utafitiHapana
    -0.34
    KommentareTeilen
    -0.34
    POSITIVE LOGITS
     communication
    0.77
     communications
    0.74
     komunikasi
    0.67
     email
    0.66
     Communication
    0.65
    Communication
    0.63
     communicating
    0.62
    communications
    0.62
    communication
    0.62
     chat
    0.60
    Activations Density 0.024%

    No Known Activations