Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15583
    Prev
    Next
    INDEX
    Explanations

    phrases expressing joy and anticipation related to reunions or strengthening connections

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

    Follows prepositions or conjunctions ("at", "like", "we")

    np_acts-logits-general · gemini-2.0-flash

    organize discussion

    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
    
    -0.74
    uguetes
    -0.73
    olella
    -0.72
    jarah
    -0.67
    WebElementEntity
    -0.65
     يتيمه
    -0.65
    argout
    -0.64
     Савезне
    -0.64
     Roskov
    -0.64
    UserScript
    -0.62
    POSITIVE LOGITS
     meeting
    2.44
     meet
    2.35
    Meeting
    2.10
     Meet
    2.06
     Meeting
    2.04
    meeting
    2.03
    meet
    2.01
     meets
    1.99
    Meet
    1.98
     met
    1.93
    Activations Density 0.188%

    No Known Activations