© 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. 128045
    Prev
    Next
    INDEX
    Explanations

    references to distances and physical movements or interactions in narrative descriptions

    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
    estión
    -0.38
     Strafe
    -0.37
     tiennent
    -0.35
     secretos
    -0.34
    AddTagHelper
    -0.34
     consigo
    -0.34
    Kenmerken
    -0.34
     glisser
    -0.34
    φή
    -0.33
     gestionar
    -0.33
    POSITIVE LOGITS
    Datuak
    0.60
    EndContext
    0.59
     yonder
    0.59
     queſta
    0.57
     ujednoznacz
    0.57
    richTextPanel
    0.56
    OGND
    0.55
     lenker
    0.52
     betweenstory
    0.52
     AssemblyTitle
    0.51
    Activations Density 0.031%

    No Known Activations