© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 13246
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or equations containing variables or operators

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

    mathematical superscript notation, particularly the closing curly brace of exponents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.67
    ViewFeatures
    -0.57
     nôtre
    -0.55
     lenker
    -0.53
     estimés
    -0.53
    脚注の使い方
    -0.52
    RefNanny
    -0.52
     vôtre
    -0.51
     berço
    -0.50
     ویکی‌پدی
    -0.49
    POSITIVE LOGITS
     Zionist
    0.43
    igail
    0.42
     $\
    0.40
     Truman
    0.40
     Texan
    0.40
     ريال
    0.39
     Goldman
    0.39
     Nixon
    0.39
    faculty
    0.39
     Reid
    0.38
    Activations Density 0.720%

    No Known Activations