© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2633
    Prev
    Next
    INDEX
    Explanations

    phrases related to clothing and fashion details

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

    descriptions of clothing items and garments worn by people.

    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
    новниш
    -0.49
    TypedDataSet
    -0.46
     bougies
    -0.44
    styleable
    -0.44
     comunale
    -0.42
    ⋱
    -0.41
    OGND
    -0.41
    pédie
    -0.41
    ddots
    -0.40
    bindingNavigator
    -0.40
    POSITIVE LOGITS
     sleeves
    1.23
     shirt
    1.11
     sleeve
    1.05
     shirts
    1.05
     Sleeves
    0.93
    Shirt
    0.90
     Shirt
    0.89
    shirt
    0.86
     sleeved
    0.83
     Shirts
    0.83
    Activations Density 0.186%

    No Known Activations