© 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. 31-GEMMASCOPE-RES-16K
    11. 5944
    Prev
    Next
    INDEX
    Explanations

    statistical terms and their application in scientific discussions

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

    sequences where "the" is followed by a noun, particularly in academic or technical texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    words that appear frequently in technical and scientific documentation.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     extremely
    -0.39
     highly
    -0.39
     svært
    -0.38
     äußerst
    -0.38
     very
    -0.38
     velmi
    -0.38
     often
    -0.36
     incredibly
    -0.35
     ogrom
    -0.35
     widely
    -0.35
    POSITIVE LOGITS
    parsedMessage
    0.73
    transQ
    0.72
     Meksiku
    0.69
    تقاوى
    0.69
     computation
    0.68
    ſammen
    0.68
     transfieras
    0.66
    RegressionTest
    0.64
     interpolation
    0.63
     INTERESAR
    0.63
    Activations Density 2.980%

    No Known Activations