© 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 - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 125
    Prev
    Next
    INDEX
    Explanations

    patterns related to categories and relationships in structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Category:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.63
     propOrder
    -0.62
    enumi
    -0.56
    parsedMessage
    -0.54
    LookAnd
    -0.54
     Infórmanos
    -0.54
    httphttps
    -0.51
    tagHelperRunner
    -0.51
    simpleType
    -0.50
    rawDesc
    -0.50
    POSITIVE LOGITS
     covering
    0.32
     slow
    0.31
     slower
    0.29
     contou
    0.28
     komis
    0.28
     $\
    0.28
    Unnamed
    0.28
    InjectAttribute
    0.27
     suje
    0.27
     new
    0.27
    Activations Density 0.437%

    No Known Activations