© 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. 19-GEMMASCOPE-RES-16K
    11. 11859
    Prev
    Next
    INDEX
    Explanations

    punctuation related to em dashes and related symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ponses
    -0.69
    TagMode
    -0.68
    PutMapping
    -0.65
     bezeichneter
    -0.64
    خواندن
    -0.64
    ViewFeatures
    -0.61
    fauteuil
    -0.61
     esternos
    -0.61
    ған
    -0.59
    ografija
    -0.59
    POSITIVE LOGITS
    ————————————————
    0.99
    awtextra
    0.98
     ujednoznacz
    0.87
    ————————
    0.87
    ––––
    0.83
    ----------------
    0.81
    —————
    0.81
    ————
    0.80
    ———
    0.79
    ---------------
    0.78
    Activations Density 0.594%

    No Known Activations