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. 20-GEMMASCOPE-RES-16K
    6. 10121
    Prev
    Next
    INDEX
    Explanations

    terms related to financial performance and market dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    that start sentences and connect clauses

    np_acts-logits-general · gemini-2.0-flash

    transition words introducing explanation or consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }))
    
    -0.55
    ++
    
    -0.54
    chman
    -0.51
     ()
    
    -0.51
    MessageTagHelper
    -0.51
    oredCriteria
    -0.50
    softc
    -0.50
    stdc
    -0.48
    MetaObject
    -0.48
     estimés
    -0.48
    POSITIVE LOGITS
    Moreover
    1.07
     Moreover
    1.03
     asimismo
    0.94
     Hence
    0.93
     hence
    0.92
     därför
    0.91
     moreover
    0.90
     Therefore
    0.88
    Hence
    0.87
    Furthermore
    0.85
    Activations Density 0.348%

    No Known Activations