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. 10179
    Prev
    Next
    INDEX
    Explanations

    references to scientific methods and research protocols

    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
     يتيمه
    -0.99
     Normdatei
    -0.87
     للاسماء
    -0.85
    yntaxException
    -0.81
     дописавши
    -0.77
     Administrativna
    -0.76
     utafitiHapana
    -0.76
     estekak
    -0.76
    🏻‍♀️
    -0.75
    matchCondition
    -0.75
    POSITIVE LOGITS
     (
    0.74
     which
    0.64
    ,
    0.64
     of
    0.55
     thingy
    0.53
    XmlAccessType
    0.52
     family
    0.51
     used
    0.51
     ​​
    0.50
     group
    0.50
    Activations Density 1.421%

    No Known Activations