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. 12972
    Prev
    Next
    INDEX
    Explanations

    programming language structure and syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ValueStyle
    -0.52
     تانيه
    -0.52
    
    -0.51
     שוליים
    -0.50
     frugal
    -0.47
     Pot
    -0.47
     Obs
    -0.47
    liquez
    -0.46
    Pot
    -0.46
    okovic
    -0.46
    POSITIVE LOGITS
    name
    1.23
    setName
    1.06
    getName
    1.06
     setName
    1.04
     name
    1.03
    Name
    1.01
    NAME
    1.00
     nameless
    0.99
     Name
    0.97
     NAME
    0.96
    Activations Density 0.073%

    No Known Activations