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. 4121
    Prev
    Next
    INDEX
    Explanations

    phrases that express preference or choice, particularly using the term "rather."

    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
    PerformLayout
    -0.68
    jspx
    -0.65
    tagHelper
    -0.63
    DataAnnotations
    -0.59
     Вікіпе
    -0.58
    Pró
    -0.57
    WriteAttribute
    -0.55
    /*
    -0.55
    endous
    -0.54
     calendriers
    -0.54
    POSITIVE LOGITS
     préfère
    1.12
     prefer
    1.09
     préfé
    1.02
     prefers
    1.00
    prefer
    0.98
     prefier
    0.94
     liever
    0.94
     préférable
    0.91
     preferring
    0.89
     prefi
    0.87
    Activations Density 0.135%

    No Known Activations