© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 14158
    Prev
    Next
    INDEX
    Explanations

    terms related to contracts and formal agreements in the context of construction and maintenance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 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
    StoryboardSegue
    -0.68
    homonymie
    -0.65
    ValueGenerated
    -0.62
    migrationBuilder
    -0.59
     nullptr
    -0.58
    NameInMap
    -0.56
     useCallback
    -0.56
    TypedDataSet
    -0.54
    rungsseite
    -0.54
     Dobson
    -0.53
    POSITIVE LOGITS
     Earn
    0.70
     rates
    0.63
    Earn
    0.62
     Rates
    0.59
    Rates
    0.58
     stores
    0.55
     متعلقه
    0.53
     Tender
    0.53
     Stores
    0.53
     Bid
    0.52
    Activations Density 0.073%

    No Known Activations