© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2638
    Prev
    Next
    INDEX
    Explanations

    references to promises, pledges, and commitments

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

    semantically similar to "promise"

    np_acts-logits-general · gemini-2.0-flash

    promises, pledges, and vows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    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
    contentLoaded
    -0.37
     resourceCulture
    -0.37
    BrowserModule
    -0.34
    millimeters
    -0.34
    IUrlHelper
    -0.34
    ⟬
    -0.34
    protoc
    -0.33
    FXMLLoader
    -0.32
     daylight
    -0.32
    MessageOf
    -0.32
    POSITIVE LOGITS
     promise
    1.34
     promises
    1.28
     promised
    1.26
     promesa
    1.16
     promessa
    1.09
     promesse
    1.09
     pledges
    1.06
     vow
    1.06
     pledge
    1.05
    promise
    1.04
    Activations Density 0.305%

    No Known Activations