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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7756
    Prev
    Next
    INDEX
    Explanations

    references to estate sales and personal possessions

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

    auctions, thrifting, or salvage

    np_acts-logits-general · gemini-2.0-flash

    thrift, antiques, and liquidation sales

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addCriterion
    -0.57
    invokeLater
    -0.50
    ResponseWriter
    -0.48
    setVerticalGroup
    -0.47
    bootstrapcdn
    -0.47
    ModelSerializer
    -0.47
    rrggbb
    -0.46
     CreateTagHelper
    -0.45
     protoimpl
    -0.43
    getMenuInflater
    -0.42
    POSITIVE LOGITS
     thrift
    0.71
     antiques
    0.69
     salvage
    0.66
     junk
    0.65
    clearance
    0.63
     liquidation
    0.62
     dumpster
    0.62
     clearance
    0.61
     antique
    0.60
     recycling
    0.60
    Activations Density 0.183%

    No Known Activations