© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3083
    Prev
    Next
    INDEX
    Explanations

    sections and elements related to blog organization and interactivity

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    blog post metadata and structural elements like timestamps, navigation links, and post categorization.

    oai_token-act-pair · claude-4-5-haiku
    Triggered 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
    Negative Logits
    AddTagHelper
    -0.54
    verifyException
    -0.43
     dė
    -0.43
     betweenstory
    -0.43
    Predecesor
    -0.42
    delwed
    -0.41
    RequiresApi
    -0.40
    Dtor
    -0.40
    onuclear
    -0.40
    تقاوى
    -0.40
    POSITIVE LOGITS
     Blog
    0.81
    blog
    0.80
     blog
    0.79
    Blog
    0.76
     posts
    0.76
     RSS
    0.75
     Archives
    0.75
     archives
    0.73
    posts
    0.69
     Posts
    0.69
    Activations Density 0.361%

    No Known Activations