© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 13585
    Prev
    Next
    INDEX
    Explanations

    references to specific artistic events or movements

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

    event names and dates, particularly those associated with major shows, fairs, and exhibitions.

    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
     solidaridad
    -0.40
     varones
    -0.35
    AndroidJUnit
    -0.35
     inflación
    -0.34
     secuencia
    -0.33
     carburant
    -0.32
     Belast
    -0.32
    bootstrapcdn
    -0.32
     Unterricht
    -0.32
     ExecuteAsync
    -0.32
    POSITIVE LOGITS
     booth
    1.36
     exhibitors
    1.35
     exhibition
    1.31
     expo
    1.27
     Exhibition
    1.26
     Exhibit
    1.26
     exhibit
    1.24
     booths
    1.23
    Exhibit
    1.23
     Expo
    1.23
    Activations Density 0.161%

    No Known Activations