© 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
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 6387
    Prev
    Next
    INDEX
    Explanations

    references to toys and collectibles, particularly American Girl dolls and action figures

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

    references to toys and collectible items, particularly action figures and dolls.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BufferException
    -0.61
    AndEndTag
    -0.59
    
    -0.56
     '\\;'
    -0.50
    lccn
    -0.49
    EnableWeb
    -0.48
    LayoutStyle
    -0.48
     autorytatywna
    -0.48
     Winaray
    -0.47
     zijne
    -0.47
    POSITIVE LOGITS
     toy
    1.55
     toys
    1.51
     dolls
    1.37
     doll
    1.30
    toy
    1.23
     Toys
    1.21
     Toy
    1.20
    toys
    1.19
    Toy
    1.13
    玩具
    1.06
    Activations Density 0.207%

    No Known Activations