© 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. 27-GEMMASCOPE-RES-16K
    11. 9640
    Prev
    Next
    INDEX
    Explanations

    concepts related to spatial distribution and concentration of elements or particles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.37
    Uid
    -0.36
     peł
    -0.35
    vedev
    -0.35
     feroit
    -0.34
     sukienka
    -0.33
    pædia
    -0.33
     Ausblick
    -0.32
     Demokratie
    -0.32
     BACKGROUND
    -0.32
    POSITIVE LOGITS
     concentrated
    1.37
    concentr
    1.16
     Concentr
    1.16
    集中
    1.12
     concentrating
    1.11
    Concentr
    1.08
     concentrate
    1.07
     concentr
    1.07
     concentrates
    1.07
     concentrado
    1.04
    Activations Density 0.675%

    No Known Activations