© 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 - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8597
    Prev
    Next
    INDEX
    Explanations

    references to promises or commitments made by individuals

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

    the word "promise" and its immediate context.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nosotros
    -0.28
    userModel
    -0.28
     \
    -0.27
     Rus
    -0.26
    sters
    -0.26
    usermodel
    -0.26
    LayoutInflater
    -0.25
    servlet
    -0.25
     st
    -0.23
    loginButton
    -0.23
    POSITIVE LOGITS
     disambiguazione
    0.82
     Promise
    0.81
    tagHelperRunner
    0.78
     lenker
    0.73
    promise
    0.72
     promise
    0.72
     estekak
    0.71
    tableFuture
    0.71
     Promises
    0.70
    endphp
    0.69
    Activations Density 0.207%

    No Known Activations