© 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. 16-GEMMASCOPE-RES-16K
    6. 13086
    Prev
    Next
    INDEX
    Explanations

    references to conditions or processes that involve order or sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kohdetta
    -0.38
     pyplot
    -0.35
    __()
    -0.35
    kirakan
    -0.35
     مرئيه
    -0.33
     становника
    -0.32
    ViewImports
    -0.32
     lot
    -0.32
     للمعارف
    -0.32
    DateString
    -0.32
    POSITIVE LOGITS
     Sobald
    0.72
    Once
    0.70
     Once
    0.69
     sobald
    0.62
    once
    0.62
     once
    0.62
    UserScript
    0.58
    請繼續往下閱讀
    0.57
     ONCE
    0.57
     nachdem
    0.57
    Activations Density 0.168%

    No Known Activations