Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 13839
    Prev
    Next
    INDEX
    Explanations

    references to the evening or late day activities and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    スマ
    -0.54
     An
    -0.51
    PTR
    -0.50
    abstractmethod
    -0.50
     aras
    -0.50
     跳转至
    -0.49
     planche
    -0.48
    ெ
    -0.48
     sun
    -0.48
    strar
    -0.48
    POSITIVE LOGITS
     evening
    1.76
    evening
    1.65
     EVENING
    1.61
     Evening
    1.60
     evenings
    1.59
    Evening
    1.48
     tonight
    1.40
     Tonight
    1.37
     night
    1.35
    Tonight
    1.34
    Activations Density 0.120%

    No Known Activations