© 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. 9-GEMMASCOPE-RES-16K
    11. 8431
    Prev
    Next
    INDEX
    Explanations

    language that relates to conflict, manipulation, and political themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.47
     muualla
    -0.42
    󠁴
    -0.40
    cessite
    -0.38
    хьтан
    -0.38
     audits
    -0.37
    ayuno
    -0.37
    Życiorys
    -0.37
    pieler
    -0.36
     personalizar
    -0.34
    POSITIVE LOGITS
    ReusableCell
    0.53
    inSlope
    0.44
    tagHelperRunner
    0.44
    VYMaps
    0.43
    invokeLater
    0.42
    BagConstraints
    0.42
    outSlope
    0.41
    Televis
    0.41
     InputDecoration
    0.41
     leaſt
    0.41
    Activations Density 0.777%

    No Known Activations