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. 1-GEMMASCOPE-RES-16K
    6. 4800
    Prev
    Next
    INDEX
    Explanations

    specific medical conditions, genetic terms, and elements of scientific formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Den
    -0.53
    mya
    -0.52
     art
    -0.51
    ifornie
    -0.48
     trinh
    -0.48
     ден
    -0.48
     ingenious
    -0.47
     den
    -0.47
     distanciation
    -0.45
     Listing
    -0.45
    POSITIVE LOGITS
    SourceChecksum
    0.79
    Personensuche
    0.79
    ast
    0.65
    strcmp
    0.62
    ven
    0.62
     MaterialApp
    0.62
    penup
    0.61
     chi̍t
    0.61
    verwijspagina
    0.61
    rativa
    0.60
    Activations Density 1.948%

    No Known Activations