Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 92374
    Prev
    Next
    INDEX
    Explanations

    specific descriptors related to fashion, particularly focusing on clothing styles and details

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

    clothing shapes and features

    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-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
    PerformLayout
    -0.74
     <<<<<<<<<<<<<<
    -0.70
    ViewFeatures
    -0.63
    发表于
    -0.58
    ]")]
    -0.57
     disambiguazione
    -0.53
    thodon
    -0.53
     pinulongan
    -0.52
     zwiſchen
    -0.52
     imagui
    -0.52
    POSITIVE LOGITS
     skirts
    0.41
     dance
    0.40
    XtraGrid
    0.35
     skirt
    0.35
     layers
    0.35
    wow
    0.34
     whir
    0.34
     tulle
    0.33
     motion
    0.33
     whirl
    0.32
    Activations Density 0.004%

    No Known Activations