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. 0-GEMMASCOPE-RES-16K
    6. 7000
    Prev
    Next
    INDEX
    Explanations

    the word "earn" and its different forms, indicating a focus on earning or income generation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <
    -0.54
     defaultstate
    -0.53
    subsubsection
    -0.52
    #[
    -0.52
    SourceChecksum
    -0.50
     redor
    -0.50
     üzer
    -0.48
    禁
    -0.46
    !
    -0.46
    5
    -0.45
    POSITIVE LOGITS
     earn
    1.48
     earning
    1.42
     earns
    1.36
    earn
    1.31
    earning
    1.23
     Earn
    1.23
     earnings
    1.17
    Earn
    1.16
    earnings
    1.08
     earned
    1.04
    Activations Density 0.181%

    No Known Activations