© 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. 2-GEMMASCOPE-RES-16K
    6. 13954
    Prev
    Next
    INDEX
    Explanations

    specific terms or references related to the Premier League and chronic diseases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     envers
    -0.51
    rrggbb
    -0.51
    mær
    -0.51
     vœ
    -0.50
     beira
    -0.48
     estatua
    -0.47
     Capacidad
    -0.47
     videa
    -0.47
     Gestión
    -0.47
     invitaciones
    -0.46
    POSITIVE LOGITS
     Premier
    0.65
     petition
    0.61
    Premier
    0.60
     chronic
    0.60
    tmp
    0.53
     PREMIER
    0.51
    EndContext
    0.50
    chronic
    0.50
    Chronic
    0.49
     petitions
    0.47
    Activations Density 0.169%

    No Known Activations