© 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-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 2724
    Prev
    Next
    INDEX
    Explanations

    phrases that denote uncertainty or variability in experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iParam
    -0.52
     ferdig
    -0.52
     californ
    -0.50
    لاثة
    -0.49
    ReactDOM
    -0.49
    TProtocol
    -0.49
    ServerSocket
    -0.48
    unjang
    -0.48
    ='#
    -0.47
     #{
    -0.47
    POSITIVE LOGITS
    Sometimes
    1.30
     Sometimes
    1.27
     sometimes
    1.25
    sometimes
    1.21
     parfois
    0.95
     quelquefois
    0.94
     бывает
    0.94
     manchmal
    0.93
     oftentimes
    0.93
     veces
    0.88
    Activations Density 0.105%

    No Known Activations