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
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 129858
    Prev
    Next
    INDEX
    Explanations

    references to image-related elements in a code context

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

    android layout elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     texts
    -0.57
     textes
    -0.56
    TextUtils
    -0.52
    AttributedString
    -0.50
     string
    -0.49
     textual
    -0.49
     namanya
    -0.47
     strings
    -0.46
     captions
    -0.45
     TextEditing
    -0.45
    POSITIVE LOGITS
     imageView
    0.72
    ImageView
    0.72
     ImageView
    0.70
    imageView
    0.67
    RenderAtEndOf
    0.60
     UIImageView
    0.59
     iv
    0.58
    ISupport
    0.54
     Савезне
    0.54
     Iv
    0.52
    Activations Density 0.007%

    No Known Activations