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. 20-GEMMASCOPE-RES-131K
    6. 130913
    Prev
    Next
    INDEX
    Explanations

    programming terminology and elements related to object-oriented programming

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

    Programming language code elements including class names, function calls, and library references, often within namespace structures.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     büyü
    -0.36
     egna
    -0.33
     dibawa
    -0.33
     acontecer
    -0.32
     nieuws
    -0.32
    IntoConstraints
    -0.31
     éc
    -0.31
     przeciw
    -0.31
    ydı
    -0.31
     świę
    -0.31
    POSITIVE LOGITS
    хьтан
    0.65
    outSlope
    0.61
     juſ
    0.60
     ſte
    0.58
    ServiceTest
    0.55
     faſt
    0.55
    ſelves
    0.54
     leſs
    0.54
     Jefus
    0.54
    الحياه
    0.54
    Activations Density 0.007%

    No Known Activations