© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1517
    Prev
    Next
    INDEX
    Explanations

    references to file management and data processing operations

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

    specific technical or programming terminology related to creating, manipulating, or working with files, sheets, and workbooks.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
     Exactos
    -0.55
    AndEndTag
    -0.49
    AnchorStyles
    -0.45
    Portály
    -0.44
    قایناقلار
    -0.43
     getSystem
    -0.42
     skjø
    -0.42
    errHandler
    -0.42
     Organization
    -0.42
    AZINE
    -0.40
    POSITIVE LOGITS
     AspNetCore
    0.65
     darin
    0.57
     therein
    0.53
     therefrom
    0.41
     thereunder
    0.38
    特に
    0.36
     kiến
    0.36
    مشخصات
    0.36
    其中的
    0.36
    pekte
    0.35
    Activations Density 0.737%

    No Known Activations