© 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11466
    Prev
    Next
    INDEX
    Explanations

    terms related to stuffed animals and their descriptions

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

    Statues, figures, and figurines

    np_acts-logits-general · gemini-2.0-flash

    figurines and statues

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     calientes
    -0.45
    RUnlock
    -0.41
    dcterms
    -0.40
     spoil
    -0.39
    WriteTagHelper
    -0.39
     passagem
    -0.39
     provisoire
    -0.38
     Smithfield
    -0.37
     transmisión
    -0.37
     compromise
    -0.36
    POSITIVE LOGITS
     figurines
    0.60
    richTextPanel
    0.57
     figurine
    0.53
     statues
    0.53
     statue
    0.52
    人形
    0.51
     muñeco
    0.49
     humanoid
    0.49
     boneco
    0.49
     dolls
    0.48
    Activations Density 0.135%

    No Known Activations