© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 39756
    Prev
    Next
    INDEX
    Explanations

    references to a specific software toolkit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    GEBURTS
    -0.37
    QRect
    -0.35
    saraba
    -0.35
    InstrumentedTest
    -0.34
    ="@+
    -0.32
     row
    -0.32
    PHPExcel
    -0.32
    ="
    -0.32
    endforeach
    -0.32
    ">—
    -0.31
    POSITIVE LOGITS
    toolkit
    1.91
    Toolkit
    1.18
     Toolkit
    1.13
     toolkit
    1.09
     createSlice
    0.91
     AssemblyCulture
    0.88
    IntoConstraints
    0.77
     Toolbox
    0.69
     toolbox
    0.67
    toolbox
    0.65
    Activations Density 0.000%

    No Known Activations