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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 6879
    Prev
    Next
    INDEX
    Explanations

    references to cryptocurrency and its economic implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dữ
    -0.61
    ⓧ
    -0.58
    cleros
    -0.56
    prende
    -0.51
     unrecogn
    -0.51
    SharedCtor
    -0.51
    uerre
    -0.49
     eukary
    -0.48
    =$?
    -0.48
    giarism
    -0.47
    POSITIVE LOGITS
     supply
    2.51
    supply
    2.20
     Supply
    2.09
    Supply
    2.04
     SUPPLY
    1.92
     supplies
    1.85
    SUPPLY
    1.71
     Supplies
    1.61
     availability
    1.60
    upply
    1.54
    Activations Density 0.299%

    No Known Activations