© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 79522
    Prev
    Next
    INDEX
    Explanations

    phrases indicating performance and reactions in casual or informal contexts

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

    calm, indifferent, detached

    np_acts-logits-general · gemini-2.5-flash-lite

    expressions conveying nonchalance, emotional detachment, or a restrained, deadpan tone.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    ByExample
    -0.43
     Zeppelin
    -0.41
    OfClass
    -0.41
     virgin
    -0.40
    substrate
    -0.40
     estekak
    -0.40
    InBytes
    -0.39
     restau
    -0.38
    RTEE
    -0.38
    houette
    -0.38
    POSITIVE LOGITS
     nonchal
    0.61
     calmly
    0.61
     indifference
    0.58
     indifferent
    0.51
    AndEndTag
    0.50
     indifer
    0.49
     Autorizaciones
    0.46
     shrug
    0.46
     calm
    0.46
     insuffisamment
    0.45
    Activations Density 0.127%

    No Known Activations