© 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. 25-GEMMASCOPE-RES-16K
    11. 15665
    Prev
    Next
    INDEX
    Explanations

    themes related to social and political discourse, especially concerning justice, community values, and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.85
     nonUne
    -0.60
    ClientSize
    -0.56
     Wikimedijinoj
    -0.54
    󠁴
    -0.53
    WebVitals
    -0.51
     дописавши
    -0.51
     kasarigan
    -0.50
     ouvriers
    -0.50
    HasForeignKey
    -0.50
    POSITIVE LOGITS
    +#+#
    0.40
     groupBox
    0.33
    nice
    0.32
    ailleurs
    0.32
    CE
    0.32
    Anyway
    0.32
     miguel
    0.31
     velkommen
    0.31
    NTIS
    0.31
    CAPS
    0.31
    Activations Density 0.440%

    No Known Activations