© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 108647
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to personal connections and emotional ties to loved ones, often in the context of loss or remembrance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     تضيفلها
    -0.54
    pres
    -0.45
     pres
    -0.42
    andar
    -0.41
    حوالہ
    -0.41
    enu
    -0.40
    Pkt
    -0.40
     ne
    -0.39
    ọi
    -0.39
    rid
    -0.39
    POSITIVE LOGITS
     húmedo
    0.69
     obligado
    0.55
    ſelf
    0.54
     nubes
    0.53
     nocturno
    0.53
     orgánico
    0.52
    elemField
    0.51
     redondo
    0.51
     kaarangay
    0.50
     citoy
    0.49
    Activations Density 0.286%

    No Known Activations