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 - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15807
    Prev
    Next
    INDEX
    Explanations

    technical language related to materials and processes

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

    Methods related to polishing or abrasion

    np_acts-logits-general · gemini-2.0-flash

    surface polishing and roughening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
    mybatisplus
    -0.41
     المعيارى
    -0.38
     Immunity
    -0.36
    reportWebVitals
    -0.36
    噺
    -0.35
    🔕
    -0.35
     societal
    -0.35
     sist
    -0.35
    volle
    -0.35
    льки
    -0.34
    POSITIVE LOGITS
     polishing
    1.21
     sanding
    1.13
     polish
    1.09
     sandpaper
    1.05
     sanded
    0.96
     smoothing
    0.92
     polished
    0.91
    polish
    0.91
     rough
    0.90
     grinding
    0.88
    Activations Density 0.135%

    No Known Activations