© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 2573
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "yesterday" and various types of chemical reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vaksinasi
    -0.63
     rodilla
    -0.60
     Grüsse
    -0.58
     zijne
    -0.58
     desempenho
    -0.56
     bluzka
    -0.56
     actualidad
    -0.55
     miniaturka
    -0.54
     cejas
    -0.54
     ciudadanía
    -0.54
    POSITIVE LOGITS
     VIP
    0.63
     PC
    0.62
     Reflection
    0.61
     Word
    0.59
     dem
    0.59
     Signal
    0.59
     reflection
    0.58
     Java
    0.58
     tract
    0.58
     cavity
    0.58
    Activations Density 0.263%

    No Known Activations