© 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. 38-GEMMASCOPE-RES-16K
    11. 13274
    Prev
    Next
    INDEX
    Explanations

    quantitative relationships or ratios between various substances or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.52
     الحره
    -0.39
    AddField
    -0.38
    MEDIATE
    -0.37
    BeginContext
    -0.37
    parsedMessage
    -0.35
    AnchorStyles
    -0.35
     विश्वसनीयता
    -0.35
     كومونز
    -0.35
    laint
    -0.34
    POSITIVE LOGITS
     ratio
    3.36
     Ratio
    2.94
     ratios
    2.94
    ratio
    2.86
    Ratio
    2.70
     RATIO
    2.64
     Ratios
    2.59
    ratios
    2.38
    RATIO
    2.27
     proportion
    1.80
    Activations Density 1.174%

    No Known Activations