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. 25-GEMMASCOPE-RES-16K
    6. 5973
    Prev
    Next
    INDEX
    Explanations

    references to economic statistics and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.65
     Countries
    -0.59
     continúas
    -0.57
    .*")]
    -0.57
    GOTREF
    -0.55
    onomía
    -0.54
     насељу
    -0.53
    Countries
    -0.53
     Villages
    -0.53
     Grüße
    -0.53
    POSITIVE LOGITS
    webElement
    0.59
    
    0.57
     English
    0.56
     dollari
    0.55
    ajs
    0.50
    hotos
    0.49
    ENGLISH
    0.48
    jsonwebtoken
    0.46
    SizeF
    0.46
     ویکی‌پدیای
    0.46
    Activations Density 0.260%

    No Known Activations