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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11725
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical processes and challenges in circuitry

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

    technical explanations with conditionals, particularly phrases beginning with "if," "however," or describing technical limitations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    WriteBarrier
    -0.68
     Мексичка
    -0.61
    ksikon
    -0.56
     "..\..\..\
    -0.56
    contentLoaded
    -0.55
    NUMX
    -0.55
     "..\..\
    -0.54
     otomatig
    -0.54
    脚注の使い方
    -0.53
     jScrollPane
    -0.52
    POSITIVE LOGITS
     оригіналу
    0.49
     invokingState
    0.45
    太过
    0.39
    Катего
    0.33
     terlalu
    0.31
    太
    0.31
     jullie
    0.30
     too
    0.30
    UrlResolution
    0.30
    เปล
    0.29
    Activations Density 0.691%

    No Known Activations