© 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. 7047
    Prev
    Next
    INDEX
    Explanations

    relationships involving matched pairs or control groups in the context of scientific studies

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

    technical or scientific text discussing detailed methodological procedures.

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

    pairs of related items that match, correspond, or are compared with each other.

    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
    URLException
    -0.63
     Administrativna
    -0.63
    MENAFN
    -0.60
    RTSC
    -0.55
    AndEndTag
    -0.54
     wikipagina
    -0.54
     الرياضيه
    -0.54
    RenderAtEndOf
    -0.52
     مرئيه
    -0.52
    tagHelperRunner
    -0.51
    POSITIVE LOGITS
     corresponding
    0.73
     paired
    0.71
     pairing
    0.60
     pairings
    0.59
     pairs
    0.59
     Corresponding
    0.57
    corresponding
    0.56
     matching
    0.54
     matched
    0.54
     partner
    0.52
    Activations Density 0.416%

    No Known Activations