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. 12727
    Prev
    Next
    INDEX
    Explanations

    instances or references of content that has been posted or published

    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
    getColumnIndex
    -1.07
     ExecuteAsync
    -1.07
    ArgsConstructor
    -1.04
    ImageContext
    -1.00
     aDecoder
    -0.84
    arakhand
    -0.81
    writeFieldEnd
    -0.81
    reportWebVitals
    -0.76
    getBean
    -0.72
    
    -0.72
    POSITIVE LOGITS
    Posted
    1.55
     posted
    1.54
     Posted
    1.34
    posted
    1.31
     posting
    1.21
     Posting
    1.21
     Theſe
    1.20
     Diſ
    1.10
     themſelves
    1.06
     whoſe
    1.04
    Activations Density 0.093%

    No Known Activations