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. 3-GEMMASCOPE-RES-16K
    6. 6041
    Prev
    Next
    INDEX
    Explanations

    negations or phrases that express denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KeySpec
    -0.68
    цездатний
    -0.54
    Хьажоргаш
    -0.52
    CodeDom
    -0.50
    multer
    -0.50
     PublicKey
    -0.49
     CGRect
    -0.49
     CGPoint
    -0.48
    Kanpo
    -0.47
     podla
    -0.47
    POSITIVE LOGITS
     الحره
    0.78
     ModelExpression
    0.74
    __':
    0.70
    __':
    
    0.68
     EconPapers
    0.63
     sinon
    0.60
    RequiresApi
    0.59
     ویکی‌پدیای
    0.58
     sino
    0.58
     للاسماء
    0.57
    Activations Density 0.182%

    No Known Activations