© 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. 8398
    Prev
    Next
    INDEX
    Explanations

    mentions of educational institutions and related events

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

    phone numbers and numeric contact information.

    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
     diha
    -0.38
     Whilst
    -0.37
    Whilst
    -0.34
     traductions
    -0.33
     learnt
    -0.32
     Toutefois
    -0.32
     Bupati
    -0.32
     whilst
    -0.31
     coches
    -0.31
    eqn
    -0.31
    POSITIVE LOGITS
     Singapore
    1.06
     Singapur
    0.97
    Singapore
    0.97
    APORE
    0.90
    新加坡
    0.86
     Singapura
    0.84
     singapore
    0.83
     SING
    0.80
     Straits
    0.73
     Sing
    0.71
    Activations Density 0.233%

    No Known Activations