© 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. 0-GEMMASCOPE-RES-16K
    11. 2534
    Prev
    Next
    INDEX
    Explanations

    references to sections within a document

    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
     appeal
    -0.49
     increase
    -0.43
     Shearer
    -0.42
     produced
    -0.41
    粒
    -0.39
     local
    -0.39
     limited
    -0.39
     escape
    -0.38
     treatment
    -0.38
     houden
    -0.38
    POSITIVE LOGITS
     section
    1.26
     sección
    1.06
     sections
    1.05
    section
    1.04
     للمعارف
    0.97
     seção
    0.93
    sections
    0.89
     secciones
    0.86
     SECTION
    0.86
     sezione
    0.85
    Activations Density 0.382%

    No Known Activations