© 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. 6191
    Prev
    Next
    INDEX
    Explanations

    quantitative data and relationships in scientific analyses

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

    scientific or medical technical language describing biological processes and measurements.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    clauses that introduce or elaborate on findings, results, or conclusions in scientific or technical writing.

    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
    ➟
    -0.40
    Encoding
    -0.35
    guruan
    -0.35
     Geschäft
    -0.34
    リコン
    -0.34
    تها
    -0.34
    /**
    -0.34
    locationManager
    -0.32
     Nachricht
    -0.32
    σθαι
    -0.32
    POSITIVE LOGITS
    TagMode
    0.82
    Tikang
    0.76
    AddTagHelper
    0.75
    AndEndTag
    0.73
     كومونز
    0.63
     kaarangay
    0.62
     Winaray
    0.60
    angliski
    0.60
    Diweddarwch
    0.60
    richTextPanel
    0.59
    Activations Density 0.205%

    No Known Activations