© 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. 33-GEMMASCOPE-RES-16K
    6. 11833
    Prev
    Next
    INDEX
    Explanations

    details related to clothing and accessories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.60
     otomatig
    -0.58
    IUrlHelper
    -0.57
    AndEndTag
    -0.55
    ChildScrollView
    -0.55
    queryInterface
    -0.54
    zeichnis
    -0.51
    الحياه
    -0.50
    tagHelperRunner
    -0.49
     lemari
    -0.48
    POSITIVE LOGITS
     sunglasses
    1.26
     hats
    1.20
     hat
    1.18
     glasses
    1.11
     beanie
    1.02
     Sunglasses
    0.93
     scarf
    0.91
     goggles
    0.91
     bandana
    0.90
     Hats
    0.88
    Activations Density 0.159%

    No Known Activations