© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16024
    Prev
    Next
    INDEX
    Explanations

    references to food offerings and services in a religious or spiritual context

    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
     vitae
    -0.36
    getDescriptor
    -0.36
    breadcrumb
    -0.35
     chrom
    -0.34
     swing
    -0.32
     true
    -0.30
     Presiding
    -0.30
    كويكب
    -0.29
     practice
    -0.29
    connector
    -0.29
    POSITIVE LOGITS
    httphttps
    0.71
    tagHelperRunner
    0.67
     propOrder
    0.66
     ब्रेकडाउन
    0.65
    uxxxx
    0.63
     Италијани
    0.60
     ModelExpression
    0.59
     AssemblyCulture
    0.59
    ंदीखरीदारी
    0.58
     تضيفلها
    0.57
    Activations Density 0.042%

    No Known Activations