© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7282
    Prev
    Next
    INDEX
    Explanations

    language regarding trade rumors in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trucos
    -0.51
     gustado
    -0.51
     mukana
    -0.50
     módulos
    -0.48
     ensayos
    -0.47
     ternura
    -0.47
     mukaan
    -0.47
     enamorado
    -0.47
     enseñar
    -0.46
     concierto
    -0.45
    POSITIVE LOGITS
     NBA
    0.64
    ngdoc
    0.59
     pivot
    0.56
     franchise
    0.55
     piv
    0.54
     playoff
    0.54
     draft
    0.51
     LeBron
    0.51
     NFL
    0.51
     виправивши
    0.51
    Activations Density 0.236%

    No Known Activations