© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 4656
    Prev
    Next
    INDEX
    Explanations

    phrases associated with the development and invention of new methods or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Diwedd
    -0.68
    показания
    -0.68
    stateMutability
    -0.67
    GEBURTS
    -0.66
    ICOLON
    -0.59
    Datuak
    -0.58
    脚注の使い方
    -0.57
     tény
    -0.57
    
    -0.57
    winston
    -0.57
    POSITIVE LOGITS
     devised
    1.28
     devising
    1.23
     devise
    1.03
     developed
    1.03
     élabor
    1.00
     invented
    0.99
    developed
    0.98
     Developed
    0.92
     inventing
    0.90
    élaboration
    0.86
    Activations Density 0.336%

    No Known Activations