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. 5-GEMMASCOPE-RES-16K
    6. 9932
    Prev
    Next
    INDEX
    Explanations

    phrases indicating financial constraints or the inability to afford something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessType
    -0.87
     calendriers
    -0.86
    nosaurus
    -0.81
    PerformLayout
    -0.80
    jasama
    -0.78
    andowski
    -0.78
    >>>>>>>
    -0.75
    TintMode
    -0.74
    xie
    -0.73
    zerland
    -0.72
    POSITIVE LOGITS
     afford
    1.98
    afford
    1.68
     Afford
    1.64
     affording
    1.58
     afforded
    1.41
     affords
    1.24
     affordability
    1.20
     affordable
    1.05
     Affordable
    1.05
     affor
    1.03
    Activations Density 0.072%

    No Known Activations