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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 11163
    Prev
    Next
    INDEX
    Explanations

    code elements related to cell selection and manipulation in spreadsheet applications

    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
    #![
    -0.58
    uxxxx
    -0.57
    出版年
    -0.57
    emons
    -0.55
    +#+
    -0.55
    housie
    -0.52
     Marsden
    -0.50
    inetti
    -0.49
    tees
    -0.48
    FormTagHelper
    -0.48
    POSITIVE LOGITS
     cell
    1.20
     cells
    1.16
    cell
    1.12
     Cell
    1.09
    Cell
    1.08
    sheet
    1.06
     sheet
    1.06
     Sheet
    1.04
    Sheet
    1.02
     Cells
    1.01
    Activations Density 0.144%

    No Known Activations